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

Beyond the annotations, it discloses the 20-page crawl cap, the 24-hour dedupe/cache behavior ('returned again instead of re-crawled'), the contents of the result, and the async 'running' state requiring a re-call. These are exactly the operational traits an agent needs and none appear in 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?

Front-loaded with the usage trigger, then progressively tighter detail on scope, return values, caching, and polling. Every sentence conveys actionable information with no filler.

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?

With no output schema and no annotations covering return shape, the description fully compensates by enumerating the returned artifacts and explaining the async state. An agent has everything needed to call it and interpret the response.

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% and the single `url` parameter is fully documented with an example, so the schema does the heavy lifting. The description adds a meaningful constraint by specifying the site must be *public*, which the schema does not state.

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 opens with a specific verb+resource ('Starts Corpus Plan's free audit of a public website') and enumerates the return payload (overall score, five pillar scores, top three issues, workspace link). It clearly distinguishes this from siblings like get_public_report and get_report_progress, which retrieve rather than initiate an audit.

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?

It states the trigger condition explicitly ('Use this when the user wants a website audited') and gives a polling instruction ('If the result says running, call again with the same url'). It doesn't name the retrieval siblings as alternatives, so it falls short of a full when/when-not rubric.

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