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

Beyond readOnlyHint/openWorldHint/destructiveHint, it discloses that this fetches the live remote file (network-dependent, may differ from what Google crawled), that gzipped sitemaps are unsupported, and that large sitemaps must be paged with startRow/nextStartRow. The gzip limitation in particular is a failure mode the annotations could never convey.

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?

Five short sentences, front-loaded with what it returns, then when to use it, then the caveats and paging note. Every sentence carries distinct information and nothing is repeated from the annotations or schema.

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 still covers the return shape (page URLs with lastmod, or child sitemaps), the pagination contract, and the unsupported gzip case. Nothing an agent needs in order to call it correctly 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?

Schema coverage is 50%: projectId and sitemapUrl are already documented in-schema, and the description adds little to them. It does give real meaning to startRow (paging) and reveals the nextStartRow return field, but rowLimit is never explained in either place, so compensation for the coverage gap is only partial.

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 resource ("Downloads a sitemap ... lists its page URLs with lastmod") and explicitly covers the index case ("or its child sitemaps when it is a sitemap index"). The line "This is the live file, which can differ from what Google last downloaded" implicitly separates it from list_sitemaps, which reports Google's copy, so an agent can distinguish the two without opening a schema.

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 concrete purposes and names two alternatives: compare against search_analytics_query pages, or pick URLs for inspect_urls. It also signals the live-vs-Google-copy distinction that would steer an agent toward list_sitemaps instead, though no explicit "do not use this when..." clause is present.

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