audit_seo_metadataUse this for a focused SEO/accessibility-signal check of supplied HTML. It does not fetch a live webpage; use audit_public_webpage for a URL.
| Name | Required | Description | Default |
|---|---|---|---|
| html | Yes | Raw HTML markup supplied by the user; this is not a webpage URL. |
| Name | Required | Description | Default |
|---|---|---|---|
| error | No | ||
| issues | Yes | ||
| overview | Yes | ||
| truncated | Yes | ||
| total_issues | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds meaningful behavioral context beyond annotations by clarifying that the tool operates on raw HTML rather than fetching a live webpage, which is a key behavioral boundary.
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?
Two sentences with no filler. The primary usage instruction is front-loaded, and the exclusion/alternative is stated in the second sentence. Every word earns its place.
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 single-parameter, read-only tool with an output schema and robust annotations, the description covers what the agent needs: usage intent, input type, and the key alternative route for URLs. Nothing critical 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%, and the parameter schema fully explains that 'html' is raw HTML markup and not a URL. The description reinforces this but does not add substantial semantic detail beyond the schema, so the baseline score 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 ('audit') with a clear resource ('supplied HTML') and scope ('focused SEO/accessibility-signal check'). It explicitly contrasts itself with audit_public_webpage, making sibling differentiation immediate.
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?
It directly states when to use this tool ('Use this for a focused SEO/accessibility-signal check of supplied HTML') and when not to use it ('It does not fetch a live webpage; use audit_public_webpage for a URL'). This is explicit, actionable guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Tools are mostly distinct by input mode (live URL vs supplied HTML/CSS) and check scope (HTML, CSS, JSON-LD, SEO signals, links). The main ambiguity is between audit_public_webpage and generate_validation_report, which run nearly the same checks but differ only in fetching vs supplied HTML; their descriptions call this out clearly.
All names follow a lowercase snake_case verb_noun pattern, but the set mixes four verbs (audit, check, generate, validate) for closely related validation operations. This is readable and predictable, with only minor semantic inconsistency around validate_schema_markup and generate_validation_report.
Eight tools is well within the ideal range and each covers a distinct input type or validation focus. The count feels appropriate for a web-validation server without redundancy bloating the surface.
The domain is well covered: live-page and sitemap audits, raw HTML/CSS/JSON-LD validation, SEO/accessibility signals, and broken links are all represented. Minor gaps exist, such as no dedicated accessibility validator and limited link-checking behavior, but agents can accomplish the core workflows.