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

The description explicitly states 'Read-only; no side effects and no writes,' which aligns with annotations (readOnlyHint, destructiveHint, idempotentHint). It further discloses what the tool checks (convention breaches, docs made false, net-new API without docs, broken refs) and the output format (Markdown verdict with locations, fixes, and slugs), adding value beyond the 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?

The description is a single dense paragraph that front-loads the purpose and usage. It efficiently covers what it does, what output to expect, and how to proceed. Every sentence adds value without redundancy, achieving conciseness despite 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?

The description fully explains the tool's behavior, inputs, outputs, and usage context. It details the categories of violations, the Markdown verdict format, and the workflow. No output schema exists, but the description compensates by describing the return structure, making the tool comprehensible and actionable.

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 parameters are well-documented in the schema itself. The description restates 'Pass the proposed new state of each changed file' and mentions 'deleted paths,' but does not add semantic details beyond what the schema already provides (e.g., newContent vs patch, max 20 files). Per the rubric, with high schema coverage, baseline is 3.

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 clearly states the verb ('Self-review a change') and specific resource ('about to commit BEFORE opening the PR'). It distinguishes from siblings by explaining it returns a severity-ranked list of violations and explicitly mentions propose_doc_update for doc issues, making it distinct from read-only retrieval tools like get_conventions or get_doc_gaps.

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?

The description gives explicit timing guidance: 'BEFORE opening the PR' and 'Call this as the final step of the edit flow, then fix findings and re-run.' It also implies the workflow by noting that doc issues produce a slug for propose_doc_update, indirectly indicating that tool for follow-up. This is clear when-to-use and provides an alternative path.

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