Skip to main content
Glama

Crew second opinion

crew_second_opinion
Read-only

Get an independent critique of a plan, design, or code diff before risky changes, with optional parallel reviewers whose answers you compare.

Instructions

Ask an independent reviewer (ChatGPT by default) to critique a plan, a design, or the current diff. Use it for risky work: payments, auth, migrations, concurrency. Expect disagreement; weigh it, don't just accept it. If a panel is configured (or workers is given), every member is asked at the same time and each answer comes back separately: compare them yourself.

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": {
      "subject": "<subject>"
    },
    "name": "crew_second_opinion"
  }
}

Input Schema

NameRequiredDescriptionDefault
baseNoGit ref for the diff (default HEAD)
depthNoquick: a short look around, then answer (a few turns, about 2 minutes at most). deep: each worker's full limits, for reviewing risky code. Default: deep with includeDiff, quick without.
filesNoFiles the reviewer should look at
subjectYesThe plan, design or question to review. Include your reasoning.
workersNoAsk exactly these workers (names from crew_status), all at once. Default: the configured panel, else the reviewer chain.
workspaceNoAbsolute path of the repository. Defaults to the directory Claude Code launched the server in.
includeDiffNoAttach the current working-tree diff

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.5.0
    • addedInput schema / properties / depth
      Added value: +{
      +  "description": "quick: a short look around, then answer (a few turns, about 2 minutes at most). deep: each worker's full limits, for reviewing risky code. Default: deep with includeDiff, quick without.",
      +  "enum": [
      +    "quick",
      +    "deep"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / workers
      Added value: +{
      +  "description": "Ask exactly these workers (names from crew_status), all at once. Default: the configured panel, else the reviewer chain.",
      +  "items": {
      +    "type": "string"
      +  },
      +  "minItems": 1,
      +  "type": "array"
      +}
  2. First observedv0.2.0

TDQS

A3.8/5.0
Behavior3/5

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

Annotations only declare readOnlyHint=true, and the description usefully adds that a panel is queried in parallel and answers return separately, which goes beyond the safety hint. It does not state latency or cost implications, whether the reviewer can read the workspace files, or what an error/partial-panel result looks like.

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?

Three tight sentences, front-loaded with the action and the risk criteria, then the panel behavior. Every sentence carries information; minor backtick noise is the only blemish.

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 7-parameter tool with no output schema, the description covers the workflow, default reviewer, and the shape of a panel response. It leaves return framing for single-reviewer calls and failure/latency expectations unstated, but nothing critical to invoking it 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; the description still adds meaning by explaining that supplying `workers` fans out to every named worker simultaneously and returns each answer independently. Other parameters (base, depth, files, workspace) are left entirely to the schema.

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?

A specific verb and resource: 'Ask an independent reviewer ... to critique a plan, a design, or the current diff,' plus the default backend (ChatGPT). It partly overlaps with the sibling crew_review_diff by including 'the current diff' without saying how the two differ, which keeps it out of the top band.

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?

Gives explicit when-to-use conditions ('risky work: payments, auth, migrations, concurrency') and handling advice ('weigh it, don't just accept it'). It stops short of naming alternatives such as crew_review_diff or saying when not to call it.

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