account_link
Direct link to the right account page for anything not doable in chat: billing, browser upload, report management. Hand the user the link and guide them.
Показать схему аргументов
{
"type": "object",
"required": [],
"properties": {
"section": {
"enum": [
"home",
"billing",
"upgrade",
"create",
"upload",
"reports"
],
"type": "string",
"description": "Where to send the user"
}
}
}
about
Platform documentation and info: how it works (Answer, Analytics, Custom Analytics), usage.
Показать схему аргументов
{
"type": "object",
"required": [
"topic"
],
"properties": {
"topic": {
"type": "string",
"description": "Topic: platform, manual, connectors, or a docs section"
}
}
}
agent_advisor
AI help desk: which analysis fits your question, interpreting results, fixing errors. Multi-turn.
Показать схему аргументов
{
"type": "object",
"required": [
"message"
],
"properties": {
"message": {
"type": "string",
"description": "Your question or request"
}
}
}
datasets_upload
Get your data in. Pass data as an array of row objects to create the dataset immediately and get a dataset ref ready for path resolver; omit it to get an upload link for a file only the user can reach. Add replace ref (uuid://ID:KEY) with data to REFRESH an existing dataset in place; schedules and tools holding that reference read the new data on their next run.
Показать схему аргументов
{
"type": "object",
"properties": {
"data": {
"type": "array",
"items": {
"type": "object"
},
"description": "Rows as an array of flat objects, creates the dataset in one call"
},
"expires_in": {
"type": "integer",
"default": 300,
"description": "Token expiration in seconds"
},
"replace_ref": {
"type": "string",
"description": "uuid://ID:KEY of an existing dataset to overwrite in place with `data` (the push/refresh mode)"
}
}
}
datasets_list
List and search your uploaded datasets, with fuzzy matching on name, description, and tags. Returns each dataset's uuid:// reference for use in path resolver and path tool run.
Показать схему аргументов
{
"type": "object",
"properties": {
"limit": {
"type": "integer",
"default": 20,
"description": "Max results"
},
"search": {
"type": "string",
"description": "Search by name, description, or tags"
}
}
}
discover_tools
Browse the analyses you can run: the ones you commissioned plus the platform Standard Library (prebuilt tools; each result tagged source:'own' or 'standard library'). Plain-language match; no query lists everything, your own first. Nothing fits? Commission it with path resolver.
Показать схему аргументов
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Plain-language search over your library + the Standard Library; omit to list everything"
}
}
}
tools_schema
Get an analysis's parameter schema. ALWAYS call before path tool run.
Показать схему аргументов
{
"type": "object",
"required": [
"tool_name"
],
"properties": {
"tool_name": {
"type": "string",
"description": "Name of the analysis"
}
}
}
review_estimate
The estimate as you review it WITH the user: the question as understood, the estimated answer (sample, marked), every place and its question, the page link, a review checklist. Before path bespoke.
Показать схему аргументов
{
"type": "object",
"required": [
"estimate_id"
],
"properties": {
"estimate_id": {
"type": "string"
}
}
}
adjust_estimate
Apply the user's layout wishes to the estimate's page through the layout agent; a new named arrangement, nothing overwritten, no number changes.
Показать схему аргументов
{
"type": "object",
"required": [
"estimate_id",
"instructions"
],
"properties": {
"estimate_id": {
"type": "string"
},
"instructions": {
"type": "string",
"description": "What to change, in the user's words"
}
}
}
find_precedent
Before estimating: how did we answer this objective before, on this data or any data? Prior packages and library runs with their tools, mappings, bespoke module names, method and verdicts. Platform-wide, read-only.
Показать схему аргументов
{
"type": "object",
"required": [
"objective"
],
"properties": {
"k": {
"type": "integer",
"default": 10
},
"objective": {
"type": "string"
},
"dataset_ref": {
"type": "string"
}
}
}
check_tool_fit
Before naming a library tool: does it fit THIS dataset for THIS question? Column mapping, missing required inputs, method-fit verdict, the places it delivers. Read-only.
Показать схему аргументов
{
"type": "object",
"required": [
"tool_name",
"dataset_ref"
],
"properties": {
"objective": {
"type": "string"
},
"tool_name": {
"type": "string"
},
"dataset_ref": {
"type": "string"
}
}
}
package_status
Read an analytics package back: status, every run under it, the report link once delivered.
Показать схему аргументов
{
"type": "object",
"required": [
"package_id"
],
"properties": {
"package_id": {
"type": "string"
}
}
}
my_objects
List and search the objects you own across every question: the curated charts, tables and figures of each delivered package, grouped by objective.
Показать схему аргументов
{
"type": "object",
"properties": {
"limit": {
"type": "integer",
"default": 50
},
"query": {
"type": "string"
},
"include_dropped": {
"type": "boolean",
"default": false
}
}
}
build_status
Check a commissioned build in-chat: stage progress, queue position, rejection reason if the data didn't match the objective, honest ETA, report link when delivered.
Показать схему аргументов
{
"type": "object",
"required": [],
"properties": {
"pipeline_id": {
"type": "integer",
"description": "pipeline_id from a build (modify_analysis)"
},
"track_token": {
"type": "string",
"description": "Token from the tracking URL"
}
}
}
ask_library
Ask a question across all your delivered analyses: a synthesized answer with citations back to specific reports.
Показать схему аргументов
{
"type": "object",
"required": [
"question"
],
"properties": {
"question": {
"type": "string",
"description": "Plain-language question to answer from your report library"
}
}
}
reports_list
Your report library: every analysis delivered, with status and links. Pass semantic query to search report content in plain language.
Показать схему аргументов
{
"type": "object",
"properties": {
"limit": {
"type": "integer",
"default": 10,
"description": "Max results"
},
"semantic_query": {
"type": "string",
"description": "Natural-language search over your reports' content"
}
}
}
warehouse
Query your org's data warehouse free: browse the catalog (tables with column roles + computed metrics), semantically find data, plain-language ask, or named templates. Requires warehouse enablement (business plans).
Показать схему аргументов
{
"type": "object",
"required": [
"action"
],
"properties": {
"query": {
"type": "string"
},
"action": {
"enum": [
"ask",
"query",
"queries",
"catalog",
"find"
],
"type": "string"
},
"params": {
"type": "object"
},
"question": {
"type": "string"
}
}
}
schedules
Standing re-runs of analyses you own: action='create' (weekly/monthly against a re-runnable data reference, connector:// or an https:// link; report emailed after each run), 'list', or 'cancel'.
Показать схему аргументов
{
"type": "object",
"required": [
"action"
],
"properties": {
"action": {
"enum": [
"create",
"list",
"cancel"
],
"type": "string",
"description": "What to do"
},
"cadence": {
"enum": [
"weekly",
"monthly"
],
"type": "string"
},
"tool_name": {
"type": "string",
"description": "create: the analysis to schedule"
},
"dataset_ref": {
"type": "string",
"description": "create: re-runnable reference (connector:// or https://)"
},
"schedule_id": {
"type": "integer",
"description": "cancel: from action='list'"
},
"column_mapping": {
"type": "object"
}
}
}
reports_view
Get a shareable browser link for a report, viewable without authentication.
Показать схему аргументов
{
"type": "object",
"required": [
"processing_id"
],
"properties": {
"processing_id": {
"type": "string",
"description": "Processing ID from path_tool_run / reports_list"
}
}
}
report_cards
Browse a delivered report's individual cards (charts, tables, insights) inline in chat.
Показать схему аргументов
{
"type": "object",
"required": [
"processing_id"
],
"properties": {
"processing_id": {
"type": "string",
"description": "The report's processing id, returned by path_tool_run or build_status"
}
}
}
path_resolver
Which path a question about data should take (reuse, rerun, answer, tool run, estimate, bespoke, ask or none), with the reason, every path's score and time, and the ready input for the path it picks. Executes nothing and charges nothing.
Показать схему аргументов
{
"type": "object",
"$defs": {
"MetaEntry": {
"type": "object",
"title": "MetaEntry",
"required": [
"key"
],
"properties": {
"key": {
"type": "string",
"title": "Key",
"pattern": "^[a-z0-9_.-]+$",
"maxLength": 64,
"minLength": 1
},
"note": {
"anyOf": [
{
"type": "string",
"maxLength": 200
},
{
"type": "null"
}
],
"title": "Note",
"default": null
},
"used": {
"type": "boolean",
"title": "Used",
"default": true
},
"value": {
"title": "Value",
"default": null
},
"source": {
"enum": [
"stated",
"derived"
],
"type": "string",
"title": "Source",
"default": "stated"
}
},
"description": "One piece of metadata about a question (LAT-3752; operator 2026-10-04: \"the metadata should be a list\"). The list\nis OPEN: any key is accepted. `source` says who said it: `stated` (the caller) or `derived` (the server looked it up).\nA caller can only ever produce `stated` entries; entitlement keys are read only from `derived` (meta.RESERVED).",
"additionalProperties": false
}
},
"title": "Question",
"required": [
"objective"
],
"properties": {
"door": {
"enum": [
"account",
"mcp",
"mailroom",
"widget",
"api",
"internal"
],
"type": "string",
"title": "Door",
"default": "api"
},
"meta": {
"type": "array",
"items": {
"$ref": "#/$defs/MetaEntry"
},
"title": "Meta",
"maxItems": 32,
"description": "open list of {key, value}; the caller's entries are always `stated`"
},
"objective": {
"type": "string",
"title": "Objective",
"maxLength": 4000,
"minLength": 3,
"description": "the question, in the person's words"
},
"dataset_ref": {
"anyOf": [
{
"type": "string",
"maxLength": 512
},
{
"type": "null"
}
],
"title": "Dataset Ref",
"default": null,
"description": "absent = no data yet (the resolver asks for it)"
}
},
"description": "What arrives at path_resolver from any door, after the door's own adapter has normalised it.",
"additionalProperties": false
}
path_reuse
Hand back the report already delivered for this question on this data. Time: as path resolver quotes.
Показать схему аргументов
{
"type": "object",
"title": "ReuseInput",
"required": [
"objective",
"dataset_ref"
],
"properties": {
"objective": {
"type": "string",
"title": "Objective",
"maxLength": 4000,
"minLength": 3,
"description": "the question, in the person's words"
},
"dataset_ref": {
"type": "string",
"title": "Dataset Ref",
"maxLength": 512,
"minLength": 1,
"description": "the dataset: a uuid://, upload:// or dataset id the caller owns"
},
"resolution_id": {
"type": "integer",
"description": "The resolution_id from path_resolver's path_input. Pass path_input as given."
}
},
"description": "Hand back a report already delivered on this data for this question. Re-checked at execution, never trusted\nfrom the suggestion: a report deleted or no longer the caller's is refused, not served.",
"additionalProperties": false
}
path_rerun
Run a delivered analysis again, on its own dataset or a new one: the same tools and mappings, no rebuild. Time: as path resolver quotes.
Показать схему аргументов
{
"type": "object",
"title": "RerunInput",
"required": [
"package_id"
],
"properties": {
"package_id": {
"type": "string",
"title": "Package Id",
"maxLength": 128,
"minLength": 1
},
"dataset_ref": {
"anyOf": [
{
"type": "string",
"maxLength": 512
},
{
"type": "null"
}
],
"title": "Dataset Ref",
"default": null,
"description": "absent = the package's own dataset"
},
"resolution_id": {
"type": "integer",
"description": "The resolution_id from path_resolver's path_input. Pass path_input as given."
}
},
"description": "Run a delivered package again, on its own dataset or a new one. Same tools, same mappings; no rebuild.",
"additionalProperties": false
}
path_answer
A read of the data (a total, an average, a count, the top group), computed on every row, in this response. When the question is not a read it says so and names the next step. Time: as path resolver quotes.
Показать схему аргументов
{
"type": "object",
"title": "AnswerInput",
"required": [
"objective",
"dataset_ref"
],
"properties": {
"objective": {
"type": "string",
"title": "Objective",
"maxLength": 4000,
"minLength": 3,
"description": "the question, in the person's words"
},
"dataset_ref": {
"type": "string",
"title": "Dataset Ref",
"maxLength": 512,
"minLength": 1,
"description": "the dataset: a uuid://, upload:// or dataset id the caller owns"
},
"resolution_id": {
"type": "integer",
"description": "The resolution_id from path_resolver's path_input. Pass path_input as given."
}
},
"description": "A read of the data computed on every row, in this response. Free. Abstains (immediate=false) when the question\nis not a read; it never guesses.",
"additionalProperties": false
}
path_tool_run
Run one or more tested library tools on this dataset, with charts and a written report. No custom build. Time: as path resolver quotes.
Показать схему аргументов
{
"type": "object",
"title": "ToolRunInput",
"required": [
"objective",
"dataset_ref",
"tool_names"
],
"properties": {
"objective": {
"type": "string",
"title": "Objective",
"maxLength": 4000,
"minLength": 3,
"description": "the question, in the person's words"
},
"tool_names": {
"type": "array",
"items": {
"type": "string"
},
"title": "Tool Names",
"maxItems": 8,
"minItems": 1
},
"dataset_ref": {
"type": "string",
"title": "Dataset Ref",
"maxLength": 512,
"minLength": 1,
"description": "the dataset: a uuid://, upload:// or dataset id the caller owns"
},
"estimate_id": {
"anyOf": [
{
"type": "string",
"maxLength": 128
},
{
"type": "null"
}
],
"title": "Estimate Id",
"default": null
},
"resolution_id": {
"type": "integer",
"description": "The resolution_id from path_resolver's path_input. Pass path_input as given."
},
"column_mapping": {
"anyOf": [
{
"type": "object",
"additionalProperties": {
"type": "string"
}
},
{
"type": "null"
}
],
"title": "Column Mapping",
"default": null,
"description": "dataset column for each input the tool needs; absent = suggested from the data"
},
"idempotency_key": {
"anyOf": [
{
"type": "string",
"maxLength": 128,
"minLength": 8
},
{
"type": "null"
}
],
"title": "Idempotency Key",
"default": null,
"description": "send one per run; a retry with the same key replays the first call instead of running it again"
},
"module_parameters": {
"anyOf": [
{
"type": "object"
},
{
"type": "null"
}
],
"title": "Module Parameters",
"default": null
}
},
"description": "One or more tested library tools on this dataset. One tool runs directly; several run as a library-only package\n(no custom build: that is path_bespoke).",
"additionalProperties": false
}
path_estimate
A rough answer over a sample and the layout of the full report, for the person to confirm before anything is ordered. Time: as path resolver quotes.
Показать схему аргументов
{
"type": "object",
"title": "EstimateInput",
"required": [
"objective",
"dataset_ref"
],
"properties": {
"objective": {
"type": "string",
"title": "Objective",
"maxLength": 4000,
"minLength": 3,
"description": "the question, in the person's words"
},
"tool_names": {
"anyOf": [
{
"type": "array",
"items": {
"type": "string"
},
"maxItems": 8
},
{
"type": "null"
}
],
"title": "Tool Names",
"default": null
},
"dataset_ref": {
"type": "string",
"title": "Dataset Ref",
"maxLength": 512,
"minLength": 1,
"description": "the dataset: a uuid://, upload:// or dataset id the caller owns"
},
"completeness": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Completeness",
"default": null
},
"resolution_id": {
"type": "integer",
"description": "The resolution_id from path_resolver's path_input. Pass path_input as given."
},
"layout_objective": {
"anyOf": [
{
"type": "string",
"maxLength": 2000
},
{
"type": "null"
}
],
"title": "Layout Objective",
"default": null
}
},
"description": "Free: a rough answer over a sample and the layout of the full report, for the person to confirm.",
"additionalProperties": false
}
path_bespoke
Order a custom analysis built for this data from a confirmed estimate, optionally with library tools alongside. Needs the person's yes and an idempotency key; a retry returns the first order. Time: as path resolver quotes.
Показать схему аргументов
{
"type": "object",
"title": "BespokeInput",
"required": [
"estimate_id",
"idempotency_key"
],
"properties": {
"tool_names": {
"anyOf": [
{
"type": "array",
"items": {
"type": "string"
},
"maxItems": 8
},
{
"type": "null"
}
],
"title": "Tool Names",
"default": null,
"description": "library tools to run alongside the build"
},
"estimate_id": {
"type": "string",
"title": "Estimate Id",
"maxLength": 128,
"minLength": 1
},
"resolution_id": {
"type": "integer",
"description": "The resolution_id from path_resolver's path_input. Pass path_input as given."
},
"idempotency_key": {
"type": "string",
"title": "Idempotency Key",
"maxLength": 128,
"minLength": 8
},
"layout_objective": {
"anyOf": [
{
"type": "string",
"maxLength": 2000
},
{
"type": "null"
}
],
"title": "Layout Objective",
"default": null
}
},
"description": "PAID. The order that includes a custom build, from a CONFIRMED estimate only. The idempotency key makes a retry\nor a double click replay the first order instead of placing a second (research: Stripe, IETF idempotency draft).",
"additionalProperties": false
}