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

No annotations exist, so the description fully carries the burden. It declares the tool is a 'Pure HTML parser' (no side effects), details exactly which href types are skipped, and describes the output structure. All behavioral traits are disclosed, making the tool's behavior predictable.

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 moderately concise and front-loaded with the key phrase 'Pure HTML parser.' Every sentence provides specific information, though it could be slightly shorter without losing clarity. Structure is logical.

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 the tool's simplicity, the description explains the output thoroughly (fields returned, internal vs external, skipped links) and links to its intended downstream use (compute_link_graph). No output schema exists, but the description compensates fully.

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%, with both parameters well-described in the schema. The description adds minimal extra meaning for parameters beyond what the schema provides (e.g., baseUrl used for resolution). Baseline of 3 is appropriate.

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 uses a specific verb ('extract') and clearly defines the resource (links from HTML). It explicitly states the output format (absolute, internal vs external, cleaned anchor text, rel, nofollow) and what is skipped (fragments, mailto:, etc.). This distinguishes it from siblings like compute_link_graph, which consumes its output.

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 explains that it is designed to feed compute_link_graph and that it should be called per page crawled from the user's machine. This gives clear context for when to use it, though it does not explicitly list scenarios where it should not be used (e.g., if no raw HTML is available).

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