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

Annotations cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description goes well beyond them: it discloses the fixed rule set for what gets included, the [square-bracket] gap convention with an explicit 'never stand-ins' guarantee, and the three return artifacts (letter, gaps, checklist).

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, front-loaded with the trigger and immediately followed by behavior and return values. No filler, no repetition of schema fields.

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 no-output-schema, 12-parameter generative tool, the description covers the trigger, required inputs, deterministic generation rules, missing-fact handling, and the return payload — everything an agent needs to call it correctly.

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 baseline is 3, but the description adds real meaning by explaining how inputs are consumed — up to two resume results, job title and top keywords from the posting — which tells the agent what each input actually drives in the output.

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 (draft a cover letter) plus the exact sources it draws from — the user's resume and the job posting. This clearly distinguishes it from nearby siblings like tailor_resume, draft_resignation_letter, and write_summary.

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 when the user wants a cover letter for a job,' and routes link-based input to fetch_job_post. It does not state when NOT to use it or contrast it against similar siblings such as tailor_resume, so alternative selection is left to inference.

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