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

With no annotations, the description carries the behavioral burden. It usefully discloses that the response body is discarded and that the target is a public URL, but it does not mention redirects, timeouts, request method, or error behavior. This is helpful but incomplete.

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?

The description is two short sentences with no filler: the output is front-loaded and 'Body discarded' is a meaningful behavioral detail. It earns its place despite being too sparse for the full schema.

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?

Given a 9-parameter schema, no annotations, no output schema, and multiple sibling fetch/URL-checking tools, this two-sentence description is insufficient. It does not clarify which parameters are used, what the return shape is, or how web-fetch differs from fetch-status and browser-url-ok.

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 has nine parameters (ref, url, city, feed, host, json, path, zone, query) and 100% coverage, but the description never explains which parameters are relevant to web-fetch or how the extra fields are used. The url parameter's schema description says 'HTTPS URL to normalize or cite', which conflicts with the fetch behavior stated in the tool 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 what the tool does: returns HTTP status and content type for a public URL, and it adds that the body is discarded. This is specific enough to convey the core function, though it does not differentiate web-fetch from overlapping siblings like fetch-status or browser-url-ok.

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?

The phrase 'public URL' provides an implied usage context: use this for public URLs when you need status and content type without the body. However, there is no explicit when-to-use vs alternatives, no exclusions, and no mention of why web-fetch should be chosen over fetch-status or browser-url-ok.

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