Extract Links

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

With no annotations, the description carries the full burden and does well: it discloses the no-network guarantee, the default .onion-only filtering, and the post-processing behavior ('deduplicated and grouped by host'). It stops short of error/edge-case behavior (malformed HTML, the 500k length cap), so not a 5.

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?

Three tight sentences, front-loaded with purpose and the most consequential constraint (no network access), then parameter guidance, then output shape. No filler and nothing buried.

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 3-param, no-output-schema tool this is nearly complete: it covers the safety/scope trait, defaults, and result structure. Only minor edge-case behavior (input size limits, malformed input handling) is left unaddressed, which the schema partially covers via maxLength.

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% and the schema already documents all three parameters, including the filter_onion default and base_url's role. The description's restatement adds no syntax or format detail beyond what the schema provides, so the baseline 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?

States a specific verb+resource ('Extract links from HTML') and immediately scopes it with '(no network access)', which cleanly separates it from fetch_page/download_file in the sibling set. An agent can tell at a glance that this is pure parsing, not retrieval.

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 how to steer behavior ('set filter_onion: false for all links', 'Pass base_url to resolve relative links'), which is useful operational guidance. However, it never says when to choose this tool over siblings such as page_metadata or fetch_page, nor any precondition beyond the implied need for HTML in hand.

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