Url Text

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

Beyond annotations (read-only, idempotent), the description adds that it does not execute JavaScript, respects cache, and rejects private/SSRF-sensitive URLs. This provides useful behavioral context, though 'bounded' and 'normalized' are not elaborated.

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 only 4 sentences, front-loaded with the core purpose, then constraints and parameter usage. Every sentence is essential and adds value without redundancy.

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?

With output schema present, the description covers purpose, constraints, and parameter usage adequately. It is slightly vague on the meaning of 'bounded normalized readable text', but the output schema likely fills in the details.

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 coverage is 100% with descriptions for both parameters. The tool description reinforces the schema's guidance on 'fresh' and 'url', but does not add significant new meaning beyond what the schema already provides.

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 it returns 'bounded normalized readable text' from a URL, indicating text extraction. However, the phrasing 'bounded normalized readable text' is somewhat vague and doesn't explicitly differentiate from sibling tools like url_extract or url_markdown.

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 explicitly states when to use (public HTTP(S) resources only) and when not to (no JavaScript, no access control bypass). It also gives clear guidance on the 'fresh' parameter: keep false for cache reuse, set true only when needed. However, it does not compare to sibling tools.

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