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

Annotations already cover safety (readOnly, idempotent, non-destructive), yet the description adds substantial non-schema context: no new fetch, source table, single simulated run vs aggregated CrUX, and 'charges no credits'. The remaining gap is pagination/response-size behavior, but for a cache-read tool this is strong.

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?

Front-loads what the tool is and where the data comes from, then layers constraints in descending priority. It is dense and slightly run-on, but nearly every clause carries operationally relevant information rather than filler.

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?

With no output schema, the description compensates by explaining return semantics (`allGood` computed only when all three metrics measured and good), the state classifier, cost, and error behavior. An agent has everything needed to call and interpret it.

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%, which sets the baseline at 3, but the description adds real meaning beyond the schema: the `state` filter values and their semantics, and what `pages[].allGood` encodes. The declared params (auditId, projectId) are already documented in the schema, so credit here is for the extra field/enum semantics.

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+resource (Core Web Vitals report) and pins the exact data source ('reads audit_lighthouse_results'), so an agent can distinguish it from the many get_*_report siblings at a glance. It also declares scope (per page/strategy) and the LAB-vs-field-data boundary.

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?

Explicitly tells the agent to 'ALWAYS narrow on state first' and enumerates the two meaningful states with their interpretation, plus a when-NOT ('never Search Console's real Chrome UX Report field data'). It also notes the error condition when the audit doesn't belong to the project, leaving little to inference.

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