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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds meaningful behavioral context: the definition of 'broken' (4xx/5xx), that only the latest completed crawl is sampled, and that each entry carries the referring page. It stops short of noting pagination or result caps.

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?

One well-formed sentence with the key scoping qualifier embedded, plus a docs link at the end. Nothing is redundant and the core definition of 'broken' is front-loaded.

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 an output schema, full annotation coverage, and a single required parameter, the description supplies everything an agent needs: what is returned, the crawl window, and the included referring page. No material gap remains.

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?

Only one parameter and schema description coverage is 100%, so the schema fully documents monitor_id; baseline 3 applies. The description adds no format, range, or lookup guidance beyond what the schema already says.

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 ('List the broken links') and goes further by defining what counts as broken (dead URLs returning 4xx/5xx) and pinning the scope to the most recent completed crawl. An agent can distinguish this from get_crawl_results or get_sitemaps 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 'most recent completed crawl' constraint implies the temporal boundary and helps route away from raw crawl tooling, but no sibling is named and there is no explicit when-to-use/when-not guidance. Usage is inferable rather than stated.

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