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

Annotations already cover read-only/idempotent/open-world safety, yet the description still adds real behavior: it returns text rather than writing files, the calling agent must place it at public/llms.txt or web root, and it discloses the empirical caveat that answer engines largely do not read the file. That is exactly the kind of context annotations cannot carry.

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?

Purpose and output location are front-loaded and every sentence is actionable, but the evidence paragraph (Google July 2025, Ahrefs 97%/137,210 domains) is dense and repeated in spirit two or three times ('not a visibility fix', 'not scored', 'promising a citation lift would be false'). Slightly over-tall for the single-parameter operation.

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 one-parameter generator with no output schema, it covers what is produced, where it should be written, what the human reviewer must check, and the expectation-setting caveat — nothing an agent needs to call or frame the result 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?

Only one parameter with 100% schema coverage, so the schema already documents accepted forms ('domain or full URL'). The description adds only indirect meaning via 'fetched metadata', which implies the tool fetches the site rather than using supplied page data, but gives no format or validation detail beyond the schema.

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 and artifact ('Generate an llms.txt file body') plus the source ('from its fetched metadata: site name, description and key pages'), which clearly separates it from siblings like generate_seo_fixes or generate_submission_kit that also produce files.

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 use condition ('Use when the user asks for the file knowing that'), an explicit non-use framing ('it is not a visibility fix, it is not scored by get_visibility_score'), names a sibling, and adds a procedural prerequisite ('reviewing the Key Pages list first').

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