Primavera

Start a job

start_list_job

Idempotent

Start a job on a list; it runs in the background. Each place is billed on its result, never beyond maxCredits nor the estimate: send estimate.maxCredits of estimate_list_job, with the same tool, question, criterion and scope. Follow it with get_job; results land in get_list_items.

Paid: maxCredits (the most credits this call may spend, never exceeded) and idempotencyKey (a new UUID v4 for this operation) are required; without them nothing runs. To retry after an error or a timeout, send the same idempotencyKey with the same arguments: nothing is charged twice. Ask the user before calling it.

Same call as POST /api/v1/lists/{id}/jobs of the REST API.

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": {
      "listId": "<listId>",
      "tool": "<tool>",
      "maxCredits": "<maxCredits>",
      "idempotencyKey": "<idempotencyKey>"
    },
    "name": "start_list_job"
  }
}

Input Schema

Name	Required	Description
`tool`	Yes	executives: company executives (France and the United States only); summary: 3-sentence summary of the website; question: a yes/no question asked to the website; filter: a criterion judged on the data we hold (no website read).
`scope`	No	Places the job runs on: the whole list (default), the places a finished qualification judged conforming, or those it could not decide.
`listId`	Yes	Id of a list of the account (from create_list or list_lists).
`question`	No	tool "question" only.
`criterion`	No	tool "filter" only.
`maxCredits`	Yes	The most credits this call may spend (required on every paid call, with an Idempotency-Key header). Never exceeded.
`idempotencyKey`	Yes	A new UUID v4 for this operation (sent as the Idempotency-Key of the API). Reuse it only to retry the very same call: the saved result comes back, nothing is charged twice.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 12, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Beyond the annotations, the description discloses the cost model (per-result billing, capped at maxCredits and never beyond the estimate) and the retry/idempotency behavior, which is the crucial operational context for a paid write call. The idempotentHint=true annotation is consistent with the stated retry semantics, so the description reinforces rather than repeats blindly. It stops short of describing job lifecycle states, but that is largely get_job's territory.

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?

The purpose is front-loaded, followed by billing, then required paid parameters, then the REST equivalent. Every sentence carries operational weight, though the final REST endpoint mapping is marginally useful to an agent and the middle paragraph is dense enough to require careful reading.

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

Completeness5/5

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

With no output schema, the description still tells the agent where results surface (get_list_items) and how to poll (get_job), and it covers the paid-parameter prerequisites and retry path. For a background job-start tool with full schema coverage, nothing essential is missing.

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 100%, so the baseline is 3, but the description adds real cross-tool meaning: maxCredits must be seeded from estimate_list_job's estimate.maxCredits, and the retry call must reuse the same idempotencyKey with identical arguments including tool, question, criterion and scope. That linkage is not derivable from the schema alone.

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?

The description opens with a specific verb and resource ("Start a job on a list") and immediately names its execution mode ("runs in the background"). It also distinguishes the tool from close siblings by naming get_job for polling and get_list_items for results, so an agent can place it in the workflow without opening any 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?

It gives explicit sequencing: call estimate_list_job first, pass its estimate.maxCredits here, then follow with get_job, with results in get_list_items. It also states a prerequisite action ("Ask the user before calling it") and a retry rule tied to idempotencyKey, leaving little to inference.

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

All Primavera tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.