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

Annotations already declare readOnly, idempotent, non-destructive and open-world, and the description adds substantive context beyond them: it reads the page plus robots.txt, /.well-known endpoints, sitemaps and llms.txt and up to ten same-origin bundles, explicitly never logs in, submits forms or mutates the site, and notes roughly one-hour caching. That is exactly the kind of scope and side-effect disclosure annotations cannot 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?

Front-loaded with the trigger condition, then the output, then the access behavior and caching. Four sentences, each earning its place, with no filler or repetition of the title.

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 single-input scoring tool with an output schema and full annotation coverage, the description supplies the access footprint, mutation guarantees and cache semantics an agent needs to set expectations. Return values are additionally summarized rather than left opaque, so nothing material 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?

There is a single parameter and the schema documents it fully (100% coverage, with an example). The description only implies 'one public website' and adds no syntax or format detail beyond the schema, so the baseline 3 is appropriate for a schema that already carries the parameter semantics.

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+resource ('Scores one public website out of 100 for agent readiness') with the exact deliverable (grade, sub-scores, top five fixes, scan time, cache flag). It is easily distinguished from siblings like explain_check, list_checks and watch_site because it describes a one-shot scoring action rather than an explanation, listing, or monitoring subscription.

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?

Provides explicit trigger phrasing ('Use this when the user asks whether a website is ready for AI agents... or what to fix'), which covers the main invocation context well. It does not, however, tell the agent when to prefer watch_site (ongoing monitoring) or explain_check (explaining a specific finding) over a fresh score, so the routing against siblings is incomplete.

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