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

Annotations already declare this is a read-only, idempotent, non-destructive query, so the description does not need to repeat that. It adds real value by disclosing that the data is real-user (field) data, that values are reported at a percentile with good/poor sample shares, and that `by` vs. `over_time` change the shape of the result. It does not mention pagination or row caps beyond what the schema says.

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?

It is a single dense sentence that leads with what the tool returns and then covers mode selection; no filler or repetition. The nested clauses ('set by ... or over_time ...') make it slightly harder to parse than it needs to be.

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 10 parameters, no output schema, and no nested objects, the description does a reasonable job sketching the returned content (percentile value, good/poor share, ranked or time-bucketed rows). It leaves defaults (p75, 30d) and the from/period interaction to the schema, which is acceptable, but an agent gets no explicit note that by and over_time are mutually exclusive modes.

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 90%, so the schema carries most parameter meaning. The description still adds non-obvious semantics: `by` ranks instead of returning the summary, `over_time` yields one metric per day bucket, and the percentile framing explains what the returned number means. That is meaningful added meaning beyond the per-parameter strings.

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 (real-user Core Web Vitals: LCP, INP, CLS, FCP, TTFB) and states what is returned (a percentile value plus the share of good/poor samples). It also distinguishes its two output modes (ranked `by` vs. per-day `over_time`). It never explicitly contrasts itself with siblings such as get_breakdown or get_timeseries, so it falls short of a 5.

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 gives genuine mode-selection guidance: use `by` to rank pages/countries/browsers for one metric, or `over_time` to see when a metric changed. It does not say when to prefer this tool over the 17 siblings (notably get_breakdown and get_timeseries), nor when not to use it.

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