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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=true), so the bar is lower, and the description still adds meaningful behavior: 'No AI call, nothing stored.' It also bounds the tool's claims by stating it does not measure actual citation. It does not describe rate limits, latency, or failure behavior, but the added context is genuinely useful beyond the annotations.

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 tightly packed sentences: trigger first, then the scope of checks, then limits and safety. Every sentence earns its place with no repetition of the title or schema. Front-loaded with the actionable 'Use this when' clause.

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 no output schema, the description's enumeration of the eight checks effectively previews the result dimensions, which is valuable. It stops short of describing the shape of the report or the per-check pass/fail output, but for a read-only audit tool this is close to complete. Annotations already carry the safety and open-world profile.

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% and the single 'url' parameter is already documented in the schema, including the note that a bare domain is fine. The description adds no further semantics about the URL (e.g., http vs https handling, redirects, page vs site scope). Baseline 3 is appropriate when the schema carries the parameter burden.

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 names a specific verb+resource ('check whether AI engines can read a site') and then enumerates the eight concrete checks performed, so the agent knows exactly what the tool inspects. It also explicitly delineates what it does not do ('does not measure whether any engine actually cites the site'), which separates it from check_ai_visibility. Sibling tools like check_ai_crawler_access and check_sitemap are clearly narrower in scope.

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 opens with a concrete trigger ('Use this when someone asks whether AI engines can read, crawl or quote their website, or wants an AI-readiness audit'), which is clear usage context. The negative clause excludes citation measurement, implicitly routing that need elsewhere, but no sibling is named as an explicit alternative. Strong context, but not fully explicit when/when-not routing.

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