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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds genuine behavioral value by naming the four diagnostic categories it evaluates, telling the agent what findings to expect, though it omits how results are returned or whether it mutates nothing beyond reading input.

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 dense sentence, front-loaded with the verb and resource, then the enumerated checks in priority order. No filler or restatement 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 read-only, three-parameter diagnostic with no output schema and fully documented parameters, the description gives enough to invoke correctly. Only a hint about the shape of the returned report is missing, which is minor.

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%, including format examples (Origin URL string, key-value map or "Header: Value" list) and the credentials flag default. The description adds no parameter-level meaning beyond the schema, so the baseline 3 applies.

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 (Analyze) and resource (CORS request/response headers) and enumerates the exact classes of findings it produces: wildcard/credential violations, missing Vary: Origin, preflight OPTIONS handling, header exposure. No sibling tool covers CORS, so it is unambiguous against the list.

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?

Usage is implied by the input shape (you supply an Origin and response headers), but there is no explicit statement of when to reach for this tool or what it does not cover, e.g. no mention of whether it can be used for preflight-only debugging or server-config auditing.

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