Review brief

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

Beyond the readOnlyHint annotation, it discloses the brief's contents (verdict, ranked hunks, questions, skim-safe files, unranked-hunk count), the dual Markdown/structured return, the determinism guarantee, and an explicit prompt-injection warning about quoted and backticked text. That is unusually rich behavioral context for a read-only tool.

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?

The usage trigger is front-loaded and every clause carries information (sources, return shape, contents, injection caveat). It is a dense two-sentence block rather than a bloated one, though the enumeration of brief sections is long.

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?

An output schema exists, so return-value structure does not need explaining, and the description nonetheless covers purpose, trigger, provenance, and the safety caveat. Nothing an agent needs to invoke this correctly 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 base, head, repoDir and maxTokens are already fully documented in the schema. The description only alludes to the two-ref diff and adds no format details, 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 names a specific artifact (a deterministic review brief for the changes between two git refs) and states its provenance (git history plus the import graph, not code reading), which meaningfully separates it from score_diff. It never names a sibling tool, so differentiation is inferential rather than explicit.

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?

"Call before reviewing a diff" gives a clear, actionable trigger for the tool. There is no explicit when-not guidance or named alternative for cases like scoring an already-summarized diff, so it stops short of a 5.

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