Latest CrUX record (raw)

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, but the description goes well beyond that by detailing the response structure (histogram bins, percentiles, fractions), data types (integer ms, string-encoded double for CLS), invariants (collectionPeriod always 28 days), normalization behavior, and the surprising '404 as {no_data:true}' convention. No contradiction with annotations.

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?

Seven sentences, each earning its place: purpose, response structure, type details, invariants, normalization, no-data handling, and alternative tool guidance. Front-loaded with the core purpose, no fluff or repetition, and logically organized.

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 must compensate, and it does thoroughly: it covers the response object's shape (histogram, percentiles, fractions), field types, edge cases (urlNormalizationDetails, no_data), and usage context (origin vs URL, fallback). This is more than sufficient for an agent to invoke the tool and interpret results correctly.

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 100%—each parameter (url, origin, metrics, form_factor) already has detailed descriptions covering mutual exclusivity, redirect behavior, fragment stripping, and device-class caveats. The tool description itself adds no parameter-specific meaning, so the baseline of 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?

The description opens with a specific verb and resource ('Returns the latest 28-day rolling CrUX record'), clarifies it is the raw API response, and explicitly contrasts it with get_core_web_vitals ('ready-made assessment' vs 'full histograms/fractions'), making it clearly distinct from siblings.

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?

It directly names the alternative tool get_core_web_vitals and states when to prefer one over the other. It also adds practical guidance about no-data answers (404 as {no_data: true}) and the daily update cadence, helping agents decide when to use this tool and how to handle expected outcomes.

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