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

Annotations already declare readOnly, idempotent, and non-destructive hints. The description adds valuable context beyond those: it does not execute JavaScript, does not bypass access controls, returns a bounded cached result, and caps output at five links. These behavioral traits are not derivable from annotations alone and help set accurate expectations.

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?

Three concise sentences carry the full message without fluff. The main purpose is front-loaded, and every sentence adds distinct value: function, constraints, and cache guidance. No redundant information.

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 tool has a simple 2-parameter surface, a rich schema, comprehensive annotations, and an output schema. The description covers all necessary operational context: what it does, URL constraints, JS/access control limitations, cache behavior, and the optional fresh flag. Nothing essential 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 100% and parameter descriptions are already detailed, which gives a baseline of 3. The description adds a bit of extra meaning by explaining that 'up to five sitemap links declared by the requested page' and reinforcing the public URL requirement. However, most of the fresh parameter semantics are mirrored from the schema, so it only slightly exceeds the baseline.

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 and resource: 'Discover up to five sitemap links declared by the requested page.' This clearly states the tool's function, scope, and output limit. It differentiates from sibling tools like web.site.robots or web.site.feeds by focusing exclusively on sitemap discovery, while also noting the public HTTP(S) requirement.

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 explicitly instructs to use only for public HTTP(S) resources and states limitations: 'does not execute JavaScript or bypass access controls.' It also provides clear guidance on the fresh parameter: 'Keep fresh=false to allow cache reuse; set fresh=true only when a new upstream fetch is required.' This tells the agent when and how to use the tool versus alternatives.

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