checklist.seo_landing_audit.v1

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It fails this: it doesn't state whether this is a read-only operation, whether it makes external HTTP requests to the URL, whether it modifies anything, or what side effects occur (e.g., does it consume crawl quota?). 'Run a checklist' implies analysis but gives no transparency about what happens behind the scenes.

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 a single concise sentence with zero filler. However, it is notably under-specified for a tool with 3 parameters including a boolean flag and an enum, so while concise, it doesn't carry enough information to be 'front-loaded' with value.

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?

An output schema exists, which offloads return-value documentation. The tool is moderately complex (3 params, enum, boolean with defaults). However, the description leaves significant gaps: the meaning of 'level' and 'include_messages' is unexplained, and no guidance on expected URL format or prerequisites. It's minimally viable but not complete for a 3-param tool with an output schema.

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 0%, so the description must compensate for documenting the parameters, but it doesn't. It doesn't explain what 'level' (error/warning) controls, what 'include_messages' returns, or what format the 'url' must be in. With an output schema present, some return details may be discoverable, but the meaning of the two optional flags is undocumented in the description entirely.

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 verb ('Run') and resource ('a standard SEO landing QA checklist') for one URL. It distinguishes the scope ('one URL' singleton) from sibling tools like 'checklist.w3c_validate_and_fix_plan.v1' which imply plan generation, and SEO meta sibling tools like 'seo.set_meta.v1' which mutate rather than audit. However, it doesn't explicitly name an alternative or contrast behavior beyond implying single-URL scope.

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 usage is for running an SEO QA check on a single landing page URL, which gives some context. But it provides no explicit when/when-not guidance, no mention of prerequisites (e.g., URL must be live/public, or already published), and no contrast with sibling tools like validation.w3c.validate_urls vs this SEO-specific audit. Usage is only weakly implied.

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