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

Annotations cover the safety profile (readOnlyHint=false, idempotentHint=false, openWorldHint=true), and the description goes well beyond them: it discloses the external service dependency, the post-hoc verbatim restoration of brand names/domains/preserve lines and the reason for it (sentence-level rewriting splits names), and a concrete cost of 1 credit per 20 words.

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 filler. The core action and the gating condition come first, the restoration caveat second, and the cost last — appropriately front-loaded and every sentence 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 4-param mutation tool with no output schema, it covers usage, side effects, restoration behavior, and cost. The one gap is that it never says what is returned (rewritten text, and whether score_after's score is included), which an agent must infer from the schema.

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 the schema already documents all four parameters. The description nonetheless adds genuine meaning by explaining the rationale behind `preserve` (the humanizer splits names, so these lines are restored verbatim afterwards), which is more than the schema's own wording conveys.

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 ('rewrite text so it no longer reads as machine-written') and names the mechanism (external humanizing service), which clearly distinguishes it from siblings like generate_social_post or check_social_job.

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 trigger: 'Use this on your own writing when score_text says it would be flagged,' naming the sibling tool that gates its use. It stops short of stating when NOT to use it (e.g. freshest drafts, non-prose content), so it falls just short of the top band.

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