extract_links

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

With no annotations, the description must carry behavioral information. It clearly defines the function as extraction from an HTML string, lists return categories, and explains parameter effects. It doesn't describe side effects, but the operation is inherently read-only and side-effect-free, which is reasonable to infer. It could explicitly state that no network request is made, but the input parameter 'html' makes this clear.

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 concise and well-organized: first the main purpose, then a usage scenario, then parameter explanations, then the return structure. Every sentence 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?

For a simple extraction tool with no output schema or nested objects, the description is fully complete. It covers input parameters, return categories, and a typical use case. No critical information is missing.

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 0% description coverage, so the description fully compensates. It explains 'html' as the input string, 'base_url' as resolving relative links, and 'only_same_origin' with its condition. This adds meaning beyond the raw 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 states a specific action ('Extract all links') on a specific resource ('HTML') and enumerates the link types (anchors, forms, scripts, images). This clearly distinguishes it from siblings like html_to_text or http_request, which have different purposes.

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?

It provides a concrete use case: 'building a crawl tree without manually grep'ing the response body.' This tells the user when to use it. However, it doesn't explicitly mention when not to use it or point to alternative tools, which would be even stronger.

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