Link Audit

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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the agent knows it's a safe read operation. The description adds valuable behavioral context beyond that: it explains the optional sample verification, the HEAD-then-GET retry logic, and the exact structure of the returned payload. This gives the agent insight into how the tool behaves without contradicting any annotations.

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-structured: the core purpose is front-loaded, followed by a clear Args list, a Returns summary, and a concrete example. It is slightly longer than strictly necessary because it repeats parameter details from the schema, but every sentence serves a purpose and the layout aids scanning. It is appropriately concise for a tool with four parameters and a non-trivial output.

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 tool with four parameters, an output schema, and no hidden prerequisites, the description is complete. It covers the full behavior (including the optional broken-link verification), the return structure is explicitly described (redundant with the output schema but still useful), and the example shows realistic invocation. Nothing an agent needs to call it correctly 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?

Schema description coverage is 100% – every parameter has a clear description, including defaults and constraints (e.g., sample_size min/max, response_format enum). The tool description largely restates these in its Args list, adding little semantic value beyond the schema. The example does clarify the interplay between check_broken and sample_size, but that is also present in the schema. Per the rubric, baseline 3 is appropriate when the schema does the heavy lifting.

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 opens with a specific verb ('Audit') and a clearly defined resource ('a page's outbound links'), then enumerates the exact aspects it covers (internal/external split, rel attributes, anchor text issues, domain distribution, broken-link verification). This specificity distinguishes it from siblings like seo_audit or meta_tags_check, which target different SEO facets. An agent can immediately recognize that this tool is the one for link-level analysis.

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 provides a concrete example query that maps to the tool, illustrating when it should be invoked ('Are there broken links...'). It also implies the tool is for outbound-link auditing rather than broader SEO checks, though it does not explicitly name alternatives or state when not to use it. The context is clear enough for correct selection, but explicit exclusions are absent.

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