Trust Engine MCP

prepare_pilot_tasks

Prepares a free model pilot by providing a CSV intake template, guidance for selecting 20–30 checked tasks and masking personal data, and offline validation of draft submissions.

Instructions

Use to prepare a free pilot ("is a cheaper model good enough on our tasks?"): returns the exact intake format (CSV template with columns id, input, expected, grader, tolerance, fields, important, notes), how to pick 20-30 tasks with checked expected answers from the owner's logs, and how to mask personal data. Pass csv_text with a draft to check it offline (format errors, task count, possible personal data); nothing is uploaded.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "prepare_pilot_tasks"
  }
}

Input Schema

Name	Required	Description	Default
`csv_text`	No
`use_case`	No

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 12, 2026

TDQS

A3.6/5.0

Behavior3/5

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

No annotations are supplied, so the description carries the full behavioral burden. It does disclose the most important trait — 'nothing is uploaded' and that checks are offline — plus what the returned material consists of. But it leaves the use_case parameter, permission needs, and any limits on draft size or number of checks unexplained.

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?

One dense paragraph that front-loads the purpose and then the mechanics, with no filler sentences. The nested parenthetical listing the CSV columns is long but earns its place by defining the intake format concretely.

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

Completeness3/5

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

An output schema exists, so return values needn't be spelled out, and the description correctly focuses on what to supply and what the tool produces. The gap is the undocumented use_case parameter and the absence of any statement about what the offline checks do or do not validate beyond the three named categories.

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

Parameters3/5

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

Schema description coverage is 0% and neither parameter has a description, so the description must compensate. It does explain csv_text well — a draft CSV whose errors, task count, and possible personal data are checked — but use_case is never mentioned, leaving half the parameters undocumented in both schema and prose.

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

Purpose4/5

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

The description names a concrete deliverable set — the CSV intake template with its exact columns, guidance for selecting 20-30 tasks with verified expected answers, and personal-data masking rules. That is far more specific than a restatement of the name. It does not explicitly differentiate itself from sibling tools such as request_pilot, which keeps it below a 5.

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

Usage Guidelines4/5

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

The opening clause scopes the tool to preparing a free pilot and answers the question it is meant to answer ('is a cheaper model good enough on our tasks?'). The second half states the conditional path clearly: pass csv_text with a draft to get an offline check. It stops short of naming when to use a sibling instead or stating prerequisites/exclusions.

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

Deploy Server