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

Annotations already disclose the full safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds one genuinely useful behavioral note: the four metric groups have differing coverage, warning the agent that absent values are expected. It still omits pagination behavior despite a cursor parameter.

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 front-loaded sentence fragment ('Per page: ...') with no filler. It is efficient, though 'each with its own coverage' is imprecise enough to be near filler, which keeps it from a 5.

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 10-parameter read tool with no output schema and 0% schema coverage, the description does far too little. It never explains filtering/sorting/pagination or the shape of the per-page result, leaving the agent to infer from enums alone.

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% across 10 parameters, including non-obvious ones like cursor, verification, resource_class, and folder. The description adds no meaning for any parameter, not even that sorting or date-range filtering is possible. The schema alone leaves most parameters opaque.

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 fragment states a resource (AI crawler requests, referral sessions, citations, Site Health findings broken down per page), which is a specific and non-tautological description. However, it never clarifies how it differs from close siblings like read_ai_traffic_url, read_ai_traffic_insights, or read_ai_referrals, and 'each with its own coverage' is vague. An agent can guess the purpose but not confidently distinguish it from neighbors.

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?

There is no when-to-use guidance, no mention of prerequisites (it takes a required project_id), and no named alternative. The 'per page' grouping dimension is the only implied usage cue, which is weak given four sibling tools reporting overlapping AI traffic metrics.

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