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

Annotations declare readOnlyHint=true, and the description adds real context beyond that: the check is deterministic and involves no model, which sets correct expectations about consistency and trust. It does not describe what a failure looks like, but the safety profile is already carried by annotations.

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

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

Two sentences, zero filler, and the operational definition of the check is front-loaded before the usage instruction. Every clause carries information.

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

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

Covers inputs, scope, and the deterministic nature of the operation with no output schema present, so the only residual gap is that the result shape (e.g., per-citation pass/fail) is unstated. Minor for a read-only verification tool.

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

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

Schema description coverage is 100%, so both parameters (text, workspace) are already documented with format hints like `server.ts:120-180`. The description adds no syntax or path-resolution detail beyond the schema, so the baseline 3 applies.

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

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

States a precise verb+resource (check file:line references in text against the repository) and enumerates the three specific assertions it validates: file existence, line existence, and identifier proximity. Nothing here overlaps with siblings like crew_second_opinion or crew_review_diff.

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

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

Explicitly tells the agent when to use it: on its own analysis before presenting it. It gives no alternatives or exclusions, but the sibling set is functionally disjoint (stats/status/recon), so no routing confusion is risked. Clear context, no when-not guidance.

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

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

readOnlyHint=true already covers the safety profile, yet the description adds genuine behavioral context: a two-tier execution model (local GPU first, ChatGPT fallback) and an important quality caveat that results are unverified leads. It does not mention latency, auth, or provider failure behavior, but it meaningfully exceeds what the annotation alone conveys.

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

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

Three tight sentences, front-loaded with the core action and zero filler. Each sentence contributes a distinct fact: what it does, when to use it, and a caveat about result reliability.

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

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

With no output schema, the description usefully sketches the return content (files, functions, stage coverage, risks) and warns the results are leads rather than proof. It stops short of describing return structure or pagination, but for a read-only recon tool it is close to complete.

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

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

Schema description coverage is 100%, so the schema already documents question, paths, and workspace with their own descriptions and an example. The description adds no syntax, format, or constraint detail beyond the schema, so the baseline 3 applies.

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

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

The description states a specific verb and resource: 'map the code relevant to a question', and enumerates the output content (files, functions, stage coverage, risks). This is clearly distinct from a citation checker or diff reviewer, though it never explicitly contrasts itself with named siblings like crew_second_opinion or crew_review_diff.

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

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

It gives a clear when-to-use condition: 'Use it before reading lots of files yourself, to save your context.' It also sets expectations with 'Results are leads to confirm, not proof.' However, it names no sibling alternative and gives no explicit when-not-to-use, so it stops short of full routing guidance.

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

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

Annotations declare readOnlyHint=true, and the description is consistent with a read-only review operation. It adds real behavioral context beyond the annotation: findings are split into 'evidence-checked (the quoted code really exists)' and 'unverified', which is output behavior the agent can't infer from the annotation alone.

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

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

Three sentences, zero waste: purpose first, then the structure of the output, then the call-to-action for when to invoke. Well front-loaded and appropriately sized for the tool's complexity.

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

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

With no output schema, the description helpfully characterizes the result shape (evidence-checked vs unverified findings) so the agent knows what comes back. Combined with fully documented optional parameters and the readOnly annotation, an agent has enough to invoke it correctly; only explicit sibling routing is missing.

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

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

Schema description coverage is 100%, so every parameter (base, focus, force, paths, workspace, includeUntracked) is already documented in the schema, including the truncation/timeout caveat on 'force'. The description adds no parameter-level detail beyond that baseline, which is appropriate when the schema does the heavy lifting.

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

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

States a specific verb+resource — 'review the current working-tree changes (staged, unstaged and new files)' — and enumerates the problem classes it hunts (bugs, security, concurrency, data-integrity). The purpose is unmistakable, though it does not name or differentiate itself from sibling tools like crew_second_opinion or crew_recon.

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

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

'Run it after making changes and before saying you're done' gives a clear triggering context and an implicit when-not (don't run before you've made changes). It stops short of naming an alternative tool or the condition that would route an agent elsewhere.

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

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

Annotations already declare readOnlyHint=true, so the non-mutating nature is covered. The description adds real context (ChatGPT is the default reviewer, disagreement is expected), but omits behavioral facts that matter for an external-model call: latency, cost, and that the reproduced request sends code/diff content to a third-party service.

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

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

Three tight sentences, front-loaded with the core purpose, then usage triggers, then a caution. No filler or restated title content.

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

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

With no output schema and full schema coverage, the description only needs to carry intent and routing; it does both competently. The missing piece is explicit routing versus crew_review_diff and the external-call caveats.

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

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

Schema description coverage is 100%, so all five parameters (base, files, subject, workspace, includeDiff) are already documented in the schema. The description only hints at the diff/plan inputs and adds no format or defaulting detail beyond what the schema states.

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

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

States a specific verb and resource: get an independent reviewer to critique a plan, design, or diff. A reader knows exactly what the tool produces. It does not, however, distinguish itself from the close sibling crew_review_diff, which also handles diff review, so the agent must guess between them.

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

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

Gives concrete triggering contexts (payments, auth, migrations, concurrency) and a usage stance ('weigh it, don't just accept it'). It stops short of a when-not rule or naming crew_review_diff as the alternative for plain diff review, which is the obvious collision case.

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

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

Annotations only declare readOnlyHint=true; the description adds real value by disclosing the data source ('local metadata-only log, no prompts or code'), the per-provider limitation (ChatGPT shows calls and time only), and that context kept out of Claude is a clearly labeled ESTIMATE. It stops short of describing output structure or pagination.

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

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

Leads with the core purpose, then packs metric list, provider caveat, estimate disclosure, and data-source note into a few dense sentences. Every clause carries information, though the metric enumeration is long enough to approach list-dumping.

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

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

With no output schema, the description correctly compensates by enumerating the returned metrics and qualifying the estimate, so an agent knows what to expect. Missing only minor items like period behavior or result ordering.

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

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

Schema description coverage is 100% and the single 'period' param is a self-documenting enum with a default, so the schema carries the burden. The description says nothing about the period parameter or its default, so baseline 3 is appropriate.

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

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

States a specific verb and resource ('Show what the crew did') and enumerates the exact metrics returned per worker, so an agent knows precisely what this returns. It does not explicitly name or distinguish itself from siblings like crew_status or crew_check_citations, despite overlapping on 'findings quote-checked vs unverified'.

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

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

Usage is only implied: the tool reports aggregate usage stats, and the mention that ChatGPT calls show calls and time only hints at data caveats but not when to pick this over crew_status. No explicit when-to-use or when-not-to-use guidance is given, and no sibling is named.

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

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

Annotations only declare readOnlyHint=true; the description adds real behavioral context beyond that — it enumerates what gets reported (config, resolved workspace, worker availability) and frames the tool as the diagnostic entry point. It stops short of describing output format or failure behavior.

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

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

Two short sentences, no filler. The capability is front-loaded and the diagnostic directive follows immediately; every clause earns its place.

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

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

For a read-only, zero-required-parameter diagnostic tool with no output schema, the description covers what is reported and when to reach for it. Only the return structure is unspecified, which is a minor gap given the tool's simplicity.

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

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

With a single parameter at 100% schema coverage, the schema already documents the workspace default behavior. The description only echoes this with 'the workspace it will read,' adding marginal meaning. Baseline 3 applies since the schema does the heavy lifting.

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

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

States a specific verb (Show) and resource (crew configuration, the workspace it reads, and which workers are available), with concrete worker categories named. It is clearly distinct in function from siblings like crew_stats or crew_recon, though it never explicitly names an alternative to differentiate against.

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

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

Gives an explicit conditional trigger: 'Run this first if another crew tool errors.' This tells the agent exactly when this tool is the right call, but does not describe the normal (non-error) invocation path or contrast against siblings for routine use.

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