fetch_url

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is covered. The description adds significant behavioral context beyond that: it discloses the cost (1 credit), the timeout and custom headers support, the unprocessed return of the body, and the specific behavior of respect_robots (recording false setting against API key and returning a warning). It also explains max_inline_chars behavior (preview + result_handle). No contradictions.

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 three sentences, front-loaded with the core purpose and immediately contrasting with siblings. Every sentence earns its place: purpose, exclusions, features, cost, and an example. No fluff, no repetition of schema details.

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 6 parameters and no output schema, the description covers all necessary decision points: what to use it for, what to avoid, what it returns, cost, and edge cases (large results). It also names the sibling tools an agent might consider. The absence of an output schema is mitigated because the description explicitly states it returns the body and also mentions status, headers, and response time. The example shows a minimal valid call. Everything an agent needs to invoke correctly is present.

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%, so the baseline is 3. The description adds value by hinting at typical header usage ('e.g. auth tokens') and by including an example that demonstrates timeout usage. It also clarifies the implication of respect_robots and max_inline_chars in context, going slightly beyond the schema descriptions. However, the schema already fully documents each parameter, so the increment is modest.

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 states a clear verb-resource pair ('fetch a URL') and immediately distinguishes itself from siblings by specifying exactly what it returns (raw body, status, headers, response time) and what it does not (HTML rendering). It names the sibling 'scrape' and the extract_* family as alternatives, making differentiation explicit.

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 description gives explicit when-to-use guidance (raw HTTP body, API responses) and when-not-to-use (HTML for reading, JS-rendered or bot-protected pages), and points to alternatives: 'scrape returns markdown from one fetch' and 'scrape, then stealth_mode'. It also includes a concrete example call, reinforcing correct invocation.

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