Get Core Web Vitals (LCP, INP, CLS) and a performance score for a page via Google PageSpeed Insights — both a lab Lighthouse run and real-user CrUX field data when available.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Full page URL to test. | |
| strategy | No | Test as mobile or desktop. Default 'mobile'. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does disclose meaningful behavior: it calls Google PageSpeed Insights, returns both a lab Lighthouse run and real-user CrUX field data, and notes that field data is only present 'when available'. It does not mention API quota usage or public-URL requirements, but the core behavioral traits are clearly stated.
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, front-loaded sentence that efficiently packs the purpose, metrics, method, and data types without redundant filler. Every clause contributes new information.
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 page-level metric tool with only two documented parameters, the description provides sufficient context for invocation: URL, strategy, and what data the response contains. Since there is no output schema, a bit more detail about response shape would be useful, but the core facts presented are enough for basic use.
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 coverage is 100%, with clear descriptions for both url and strategy (including the enum and default 'mobile'). The tool description adds no parameter-level detail beyond the output metrics, so the schema is already doing 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?
Description opens with 'Get Core Web Vitals (LCP, INP, CLS) and a performance score for a page via Google PageSpeed Insights', giving a specific verb, precise resource, and the exact metrics. This clearly distinguishes it from broader sibling tools like site_audit.
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 the tool is for page-level Core Web Vitals measurement, but does not explicitly state when to use this tool versus alternatives or when not to use it. No sibling tools are referenced as alternatives, so the agent must infer the use case from the metrics named.
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.
Most tools target distinct actions, but backlinks_for_domain and top_linkers_for_domain overlap significantly since both return ranked linking domains with authority and link counts, differing mainly in scope. The descriptions do clarify one is a full payload and the other a quick skim, so an agent can usually choose correctly.
All names are lowercase snake_case and readable, but conventions are mixed: several are noun phrases like site_audit and domain_authority_score, some are verb-first like find_link_prospects, and a couple are object-verb like schema_validate and indexnow_submit. The set is understandable but lacks a single consistent naming pattern.
13 tools is appropriate for a backlink and SEO-focused server, fitting comfortably in the well-scoped range. Each area—backlink analysis, AI visibility, site auditing, and indexing—has dedicated tools without the set feeling bloated.
The backlink workflow is well covered: scoring, listing, overlapping linkers, prospect discovery, toxic-link flags, and live verification all exist. Minor gaps remain, such as no per-URL or anchor-level backlink data and no rank-tracking or keyword research, but the core stated purpose is served without major dead ends.