audit_sitemap

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

With no annotations provided, the description carries full burden. It discloses fetching sitemap, running predict_citation, sorting, and that no engine keys are needed. It hints at rate-limit risk via the concurrency parameter description but does not detail error handling or performance guarantees.

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?

Two sentences, no wasted words. The first sentence captures the core action, the second adds sort order and value proposition. Front-loaded and efficient.

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?

The description does not specify the output format (e.g., array of objects with URL and citation score) despite no output schema. It mentions sorting but lacks details on structure. For a tool that wraps predict_citation, the return is likely consistent, but this is not explicit.

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?

All three parameters have descriptions in the schema (100% coverage). The description adds valuable context: for sitemap_url it clarifies nested sitemaps are followed, for limit it explains slicing, and for concurrency it mentions parallel calls and rate-limit risk. This goes well 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?

The description clearly states the tool fetches a sitemap and runs predict_citation on each URL, returning results sorted worst-first. It distinguishes from sibling tools by emphasizing whole-site systemic issue detection, unlike single-URL tools like predict_citation.

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?

The description implies usage for whole-site audits and notes 'Zero engine keys needed' as a prerequisite. It does not explicitly state when not to use it or name alternatives, but the context of batch processing is clear.

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