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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false. The description goes beyond these by revealing concrete behaviors: it 'automatically flags robots.txt-blocked and already-tested pages', applies a '-25 significance penalty' to legal pages, and groups parameters into three jobs (discovery, ranking/paging, filtering). This adds substantive behavioral context that the annotations do not 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?

The description is about 100 words—informative without being bloated. It front-loads the core purpose and then systematically covers flags and parameter grouping. While it could be tightened slightly, every sentence contributes useful information and no schema detail is needlessly repeated.

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 tool with 9 parameters, an output schema, and rich annotations, the description is remarkably complete. It covers the purpose, the parameter organization, the specific behavioral flags, and the legalPages tri-state use case. The existence of an output schema covers return-value details, so no major gaps remain for an agent to call the tool correctly.

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 description coverage is 100%, so each parameter is already documented. The description adds a valuable organizational layer by grouping the nine parameters into three conceptual jobs (discovery, ranking/paging, filtering) and explaining the purpose of the legalPages filter. This helps an agent understand parameter relationships beyond the flat 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 states a specific verb ('discovers and ranks URLs') and a clear resource ('from a domain's XML sitemaps'), and explains the goal ('to find the most significant pages before analyzing them'). This is distinct from all sibling tools, which concern tests, baselines, prompts, and schedules—no other tool targets sitemap discovery. The purpose is unambiguous.

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 positions the tool as a precursor to analysis ('before analyzing them') and gives explicit guidance on the legalPages filter for either dropping legal boilerplate or isolating it for a policy-coverage audit. It doesn't explicitly name alternative tools or state when not to use it, but the sibling set is clearly different, so the use case is well implied.

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