review

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

With no annotations, the description carries the full burden: it usefully discloses read-only behavior, that no checks execute, and that identical repeats add nothing. It omits significant traits implied by the schema — that an external CLI provider is invoked (model/backend), with quota cost, latency, and a consent flow ('Tag ask', 'consent' in timeout_ms) — which an agent needs before calling.

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, front-loaded sentences with zero filler; the verdict format leads and the read-only caveat follows. The closing clause 'an unchanged complete repeat cannot help' is slightly awkward phrasing but still compact and informative.

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 10 optional parameters, 90% schema coverage, and no output schema, the description fills the main gap by specifying the return format (findings plus a verdict line). What it lacks is the operational context of delegating to an external CLI agent (cost/quota, consent, latency), which is the main residual gap.

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 coverage is 90%, so nearly every parameter (scope, backend, model, session_handle, timeout_ms) is already documented in the schema itself. The description adds no parameter-level detail, so the baseline of 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 ('Independent review of Git changes') plus the exact output shape (findings, then a 'Verdict: READY'/'BLOCKED (reason)' line). That is enough to tell it apart from siblings like consult and doctor, though it never names those alternatives explicitly.

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?

'Read-only: runs no checks' and 'an unchanged complete repeat cannot help' imply boundaries and a when-not-to-repeat rule. However, no sibling is named as the alternative and there is no explicit 'use this when X, use consult when Y' routing, so the agent must infer it.

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