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

The description explicitly discloses the main behavioral trait (body is discarded) and scopes the tool to public URLs, which is useful beyond the name. However, with no annotations present, it does not cover errors, redirects, timeouts, or whether any params other than url cause side effects.

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?

Two short sentences, front-loaded, with no fluff. Every phrase adds value: what is returned, what the scope is, and what is explicitly not returned.

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 tool with seven heterogeneous parameters and no annotations or output schema, the description is too thin. It does not explain how the extra params (city, feed, json, path, ref) relate to 'a public URL,' leaving the agent to guess the expected invocation pattern.

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?

The schema provides per-parameter descriptions for all seven params, so coverage is high and the baseline is 3. The description itself adds no parameter-level guidance and actually creates ambiguity by mentioning only 'a public URL' while the schema lists seven optional params; but it doesn't contradict the schema.

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 the resource ('public URL') and the two outputs ('HTTP status and content type'), and adds the key exclusion 'Body discarded.' It does not explicitly name an action verb or compare with sibling fetch-status, but the meaning is unambiguous.

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?

No when-to-use guidance or alternatives are mentioned. Siblings like fetch-status, normalize-url, and browser-url-ok are not referenced, so the agent must infer when web-fetch is the right choice. The only implicit signal is 'public URL,' which is not enough.

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