Skip to main content
Glama

start_fit

Queue a conjoint model fit with optional settings, returning chosen hardware and estimated runtime capped at two hours. Call quote first and confirm hardware, estimate, and limit before starting.

Instructions

Queue a fit. settings (all optional, see api_reference): taste (none / diagonal / full), error_shares (list of attributes), holdout (last / none), hb_baseline, constraints, covariates, classes, compute (auto / cpu / t4 / h100). Returns the fit with compute (the hardware chosen) and progress.estimated_seconds. Every fit stops at 2 hours. Call quote_fit first, show the user the hardware, the estimate and the 2-hour maximum, and get their go-ahead.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "dataset_id": "<dataset_id>"
    },
    "name": "start_fit"
  }
}

Input Schema

NameRequiredDescriptionDefault
settingsNo
dataset_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.5/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations at all, the description carries the full burden and does disclose key behavior: every fit is capped at 2 hours, the response includes the chosen hardware and an estimated-seconds field, and user approval is required before starting. It leaves the async/queueing model implicit ('Queue' hints at background execution but never says whether the call returns immediately or how results are later retrieved) and says nothing about permissions or cost implications.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the action, followed by settings, return shape, and the approval workflow, so an agent can stop reading early if needed. The parenthetical option list is dense but each item earns its place; the only friction is the nested parentheses around 'see api_reference' and the multi-value enumerations, which are readable but slightly crowded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-parameter tool with no output schema and no annotations, the description covers the settings vocabulary, two return fields, a hard runtime limit, and the required approval flow. Remaining gaps are modest: how the queued fit is later polled (fit_status / wait_for_fit), and what happens if the 2-hour cap is hit.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0% and the settings object is an untyped free-form bag (additionalProperties: true), so the schema alone conveys nothing. The description compensates well by enumerating the recognized settings keys and the allowed values for the enum-like ones (taste, holdout, compute). It does not explain dataset_id beyond its name and defers the full settings contract to api_reference.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Queue a fit') and immediately scopes it with what the fit consumes (settings) and produces (compute, progress.estimated_seconds). It also distinguishes itself from the sibling quote_fit, which is named as the required precursor, so an agent can tell the two apart without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit precondition and workflow: 'Call quote_fit first, show the user the hardware, the estimate and the 2-hour maximum, and get their go-ahead.' This is when-to-use, what-to-do-before, and a human-approval gate, not implied guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.