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

Goes well beyond the readOnly/openWorld/destructive annotations: it discloses that reads come from stored scans (no page loaded, no page allowance spent), that a fix deployed since the last scan will not appear, that full-site crawl rows are excluded, and that baseline scans report no change figures rather than zeroes (comparedToPrevious false means unknown, not zero). These are exactly the non-obvious traits an agent needs.

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?

Front-loads the use cases and the tool's unique value before moving to return shape and caveats, and every sentence carries real information (counting granularity, baseline semantics, crawl exclusion). It is dense and somewhat long, but no sentence is filler.

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?

There is no output schema, so the description carries return-value burden and does so thoroughly: fields returned, ordering, rule-level vs element-level counting, and the baseline/comparedToPrevious edge cases. Combined with annotations covering safety, an agent has everything needed to call and interpret this tool.

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 url/limit/website are already fully documented in the schema; the baseline is 3. The description reinforces the 'url' requirement but adds no syntax or format detail beyond what the schema provides, and its counting-granularity note is about return values rather than parameters.

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 precise verb+resource: it returns every recorded monitoring scan of a single URL, newest first, with score, violations by impact, and fixed/newly-introduced counts. It explicitly distinguishes itself from the sibling score_history (whole site vs one URL) and even frames the tool as 'the only tool that names the scan where a single page regressed.'

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?

Opens with concrete triggering questions ('did my fix actually work', 'when did this page break') and names the alternative explicitly ('use score_history for the whole site'). The when-to-use and when-to-use-something-else conditions are both stated rather than left to inference.

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