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

Annotations already declare readOnlyHint, openWorldHint=false, idempotentHint and destructiveHint=false, so the description's 'side effects: none' line is redundant. It earns credit for the facts annotations do not carry: determinism, XML escaping of values, rejection of non-http(s) URLs, and hard limits of 64 KB input, 1 s per call and 1 MB result.

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?

The core sentence is front-loaded and tight, but the generic 'When:' clause consumes a large share of the text while adding no tool-specific value, and the whole block is duplicated bilingually and again inside inputSchema.description.

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 builder with an output schema and full annotation coverage, the definition supplies what an agent still needs: size/time/output limits, validation rules and determinism. Only the boilerplate 'When' clause and the unmentioned ordering/error behavior leave small gaps.

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 parameter is fully documented with an item-level description and example, which sets a baseline of 3. The description adds real meaning beyond the schema by stating that URLs are validated (non-http(s) rejected) and that values are XML-escaped, which the schema does not mention.

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 with scope: builds a sitemaps.org XML sitemap from up to 50,000 URLs with optional lastmod, changefreq and priority. It also names a concrete behavioral rule (XML-escaping each value, rejecting non-http(s) URLs) and explicitly disclaims a sibling (html-links-extract), so an agent can identify it without opening the 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?

The 'Not for' clause is the only genuinely tool-specific routing signal and it points to html-links-extract. The 'When:' clause is generic family boilerplate listing HTTP headers, tokens, IP ranges, HTML/Markdown documents and agent-readiness files, none of which this tool handles, so it does not actually tell an agent when to pick sitemap-build over url-build, xml-parse or robots-txt-check.

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