web_fetch

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

With no annotations, the description carries the full burden. It discloses key behaviors: full content extraction, markdown conversion, 100% content fidelity without summarization, and limitations (dynamic content, large page timeouts). This is useful transparency for a fetch tool, though it does not explicitly state read-only nature or error handling on invalid URLs.

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 well-organized with headers and bullet points, front-loading the main purpose. It is concise, though there is minor redundancy between 'Full Content Extraction' and 'Content Fidelity' (both imply completeness). Overall, it is compact and scannable.

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 no output schema and no annotations, the description explains the return type (structured Markdown) and mentions edge cases (dynamic content, timeouts). However, it lacks explicit differentiation from sibling tools and does not address error handling (e.g., invalid URLs) or whether any side effects occur. It is adequate but not exhaustive.

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 already provides a complete description of the 'url' parameter (valid HTTP/HTTPS web address, must be complete and accessible) with 100% coverage. The tool description repeats this accessibility guidance but adds no new parameter semantics, so the baseline of 3 applies.

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 action ('Fetches and extracts complete content from a URL') and the output (structured Markdown). It is distinct from web_search (which searches) and web_map (which likely maps links) by focusing on a single URL. The purpose is unambiguous and immediately understandable.

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 implies its use (when you have a specific URL and want its content) but does not explicitly state when to use this tool over alternatives like web_search. It provides edge cases (accessibility, dynamic content) but no exclusions or routing to siblings, leaving the choice largely to inference.

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