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

Annotations already declare readOnlyHint and destructiveHint, but the description adds substantial behavioral context: 'No account needed, nothing is stored about you' covers privacy/auth, while 'a URL can return 200 and describe a different gene entirely' explicitly discloses a subtle failure mode. This goes well beyond the annotations and helps the agent anticipate the tool's behavior.

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 concise, front-loaded sentences: the first states the core function, the second explains the dual-question warning, and the third covers privacy. Every sentence carries useful information without redundancy or fluff.

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 simple two-parameter tool, the description covers purpose, the two checks, a key failure mode, and privacy. No output schema exists, but the description implies the output (existence + entity match), and the sibling tool 'verdict_meanings' likely handles return interpretations. Slight gap: it does not specify return format or error behavior, but this is minor given the tool's simplicity.

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%, but the tool description adds meaningful context by explaining that the 'claim' is the text the URL is meant to support and that without it, only the weaker existence check is possible. This reinforces the parameter's purpose beyond the schema's description.

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 clearly states the tool's action: 'Fetch a URL and report whether it exists, and whether the source names the same entity as the claim you attach to it.' It specifies the resource (URL) and the two distinct checks, which effectively distinguishes it from any sibling tool by explaining the core conflation failure it prevents.

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 context is implied: this tool is for checking citations. It explains why the claim parameter is needed and the failure mode of relying only on HTTP status, but it does not explicitly state when to use it versus alternatives like 'verdict_meanings' or any exclusions. Thus it provides clear context but lacks explicit guidance on alternatives.

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