psi_field_data_only

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

Beyond the readOnly/openWorld annotations, the description adds real behavioral context: the 15-40 second latency expectation, the fact that a Lighthouse pass is still run server-side even though only field data is returned, and the semantics of overall_category including its null case when traffic is too low. Auth and rate limits are not covered, but this is strong added value.

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 sentences, front-loaded with the core purpose, with each following sentence adding non-redundant information (latency, category semantics). No 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?

An output schema exists, so return values needn't be explained, and safety is covered by annotations. However, the strategy parameter is entirely unaddressed despite 0% schema coverage, and there is no guidance on the relationship to psi_audit, leaving a notable gap for a two-parameter tool with an unenumerated strategy field.

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%, so the description must carry parameter meaning. It clarifies that data covers 'a URL and its origin', which adds some scope context, but it never explains the strategy parameter (mobile vs desktop, default mobile) nor the expected url format. The key behavioral parameter is left undocumented.

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 names a specific resource (CrUX field data) and scope (a URL and its origin), and the lead-in 'Only the CrUX field data' implicitly distinguishes it from sibling psi_audit, which presumably returns full Lighthouse results too. It could be sharper by explicitly contrasting with psi_audit, but an agent can tell what this returns.

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 only implied: 'Only the CrUX field data' suggests picking this when you don't want lab/Lighthouse output, but it never states when to choose this over psi_audit or names that sibling. No explicit when/when-not guidance is given.

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