Audit SEO metadata

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

Annotations already cover read-only, idempotent, non-destructive behavior. The description adds valuable context beyond those annotations: analysis happens locally, implying the HTML is not sent to an external service—a meaningful behavioral disclosure for privacy-sensitive usage. No contradiction with 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?

A single 18-word sentence that front-loads the verb and resource, then enumerates the audit scope efficiently. Every word earns its place; no filler, repetition, or hedging.

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 moderate complexity, an output schema exists for return values, annotations fully cover the safety profile, and the description enumerates the analysis areas. The only minor gap is no mention of how results are structured or presented, but the output schema handles that, so the description is complete enough for an agent to invoke it correctly.

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%, so the schema already documents htmlContent as 'Raw HTML markup to inspect locally.' The description reinforces that the input is supplied HTML and lists what will be inspected, but adds no new format, encoding, or usage details beyond the schema. Baseline 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 states a specific verb ('Analyzes'), a clear resource ('supplied HTML'), and lists concrete checks: metadata, heading structure, viewport, image alternatives, Open Graph fields. While it doesn't explicitly contrast with siblings like html.local, the SEO-audit focus makes its scope reasonably distinct from the generic HTML and screenshot tools.

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 word 'locally' and 'supplied HTML' implicitly signal that this tool is for raw HTML you already have, not for fetching a URL (contrast with html.url). However, there is no explicit when-to-use guidance, no mention of alternatives, and no exclusion statements—so the routing is left to inference.

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