Audit sitemap

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

Annotations already declare readOnly and openWorld, lowering the bar, and the description usefully adds the multi-step behavior: fetching a sitemap index, enforcing single-host URLs, sampling evenly rather than exhaustively, and aggregating findings by issue type. It names the concrete failure classes it catches (redirecting-host canonicals, redirecting sitemap URLs), which tells the agent what signal it yields. Rate limits or runtime expectations for a crawl of up to 200 pages are not stated.

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 dense sentences with the core operation front-loaded and the detection examples trailing as supporting detail. No filler, though the second sentence's example list could be trimmed without loss.

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, the description's 'summarizes issues by type' carries the return-value burden and does so adequately, and the sampling/host-check pipeline is explained. Minor gaps remain around crawl duration, rate limiting, and what a failure result looks like when the sitemap is unreachable.

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 33% — only checkHreflang is documented in the schema. The description partially compensates: 'or sitemap index' clarifies that sitemapUrl accepts both forms, and 'evenly spaced sample' hints at how sampleSize is applied. It still never states the sampling default, the 1-200 bounds, or that sampleSize controls crawl cost, so half the parameters remain semantically thin.

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 sequence (reads sitemap/index, checks host uniformity, audits a sample) on a specific resource, and names the underlying primitive (audit_page). An agent can clearly separate this sitewide crawl from single-page audit_page and from list_sitemaps/submit_sitemap.

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?

Usage is implied by the phrase 'audits an evenly spaced sample of pages with audit_page' and the sitemap-focused scope, so an agent can infer this is the sitewide option. However there is no explicit when-to-use-vs-alternatives statement (e.g., 'use audit_page for a single URL, this tool for whole-site sweeps') and no exclusions or cost warnings.

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