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

Annotations cover safety (readOnlyHint=true, destructiveHint=false), and the description adds substantial context beyond them: never applies anything, never invents numbers/sources/quotes, unsourced claims get qualified/marked/removed, unanchored patches are dropped, digit-introducing patches are flagged, and it discloses fixed cost per call up to 12 findings with free clean text.

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?

Front-loaded with the core purpose and dense with substance; nearly every clause earns its place (constraints, workflow, cost). Some sentences are run-on and pack multiple behaviors, but there is little waste.

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?

No output schema, yet the description explains what the tool returns (patches with their 'why'), how they should be applied, and the cost model. For a read-only proposal tool with full schema coverage, nothing an agent needs to call it 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 coverage is 100%, so baseline is 3, but the description adds meaning for otherwise opaque params: findings defaults to running the detector, max_findings is capped at 12, and site_id drives cost attribution. It elaborates on the cost model tied to the findings parameter.

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 ('proposes the SMALLEST find→replace patches') and names the sibling findings sources it resolves (review_writing / score_content_draft). It also distinguishes itself from the editor-model alternatives by noting 'not the lite tier' and 'never rewrites the document' vs rewrite_content.

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 clear context: invoke after review_writing/score_content_draft findings exist, and the full workflow ('Show the user each patch... then review_writing again'). It stops short of explicitly naming rewrite_content as the alternative for full rewrites, so the sibling routing is implied rather than stated.

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