Auditoría web rápida

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

Goes well past the annotations: it names the external dependency (Google PageSpeed Insights), discloses expected latency (10-20 s, max 25 s), explains the CrUX field-data branch as conditional, and gives the LCP threshold. The latency and conditional-data notes are exactly the operational context annotations cannot convey.

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?

Three tight sentences, front-loaded with the action and source, then outputs, then timing. No filler and no repetition of the title.

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?

No output schema exists, and the description compensates by listing the returned scores, LCP, and optional field data. Combined with the latency note, an agent has enough to call it and set expectations; only the response shape (units, field names) is left unspecified.

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?

With a single parameter at 100% schema description coverage, the schema already documents the accepted domain/URL format. The description adds no extra syntax or format guidance beyond what the schema provides, so baseline 3 applies.

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?

States a specific verb and resource ('Mide con Google PageSpeed Insights la portada de una web en un celular simulado') and enumerates exactly which metrics come back. It does not name or contrast with the sibling revisar_visibilidad_ia, though the domains differ enough that confusion is unlikely.

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?

Usage is implied rather than stated: the description makes clear this is a mobile-only, homepage-only audit, which implicitly scopes when it applies. There is no explicit 'use this when / don't use this when' and no mention of the alternative tool for other kinds of checks.

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

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

Annotations already declare readOnly, idempotent and openWorld, so the safety profile is covered. The description adds genuinely new behavioral context: the latency envelope (1-3 s, max 20) and the four possible verdicts including 'sin-datos' when the homepage cannot be read, which warns the agent about partial-failure outcomes. It stops short of stating failure modes, caching, or whether redirects are followed.

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?

Purpose is front-loaded and each clause enumerates a distinct check rather than padding. The density makes it a long single block, but no sentence is redundant; light punctuation grouping of the checks would improve scanability.

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?

There is no output schema, and the description compensates by naming the verdict values (si, a-medias, no, sin-datos) and the timing, so an agent knows what to expect back and how long to wait. For a one-parameter, read-only diagnostic tool this is complete.

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% and the single parameter is well documented there ('Dominio o dirección de la web... Se analiza siempre su portada'), so the description does not need to compensate. Its reference to 'la portada de una web' restates rather than extends the schema's scope note.

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?

States a specific verb and resource ('comprueba si los asistentes de IA pueden leer y citar la portada de una web') and enumerates the concrete checks performed (OAI-SearchBot access, noindex, robots.txt AI-search vs training, JS-free text, sitemap, JSON-LD, llms.txt). This is clearly distinguishable from the only sibling, medir_velocidad_movil, which measures speed rather than AI readability.

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?

Usage is implied by the diagnostics listed and by the note that the homepage is always analyzed, but there is no explicit 'use this when' framing, no prerequisites, and no direct mention of the sibling or of when a different tool would be preferable. Adequate but leaves routing to inference.

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