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

Goes well beyond the annotations: no provider call or billing, missing Perplexity/Gemini integrations are surfaced explicitly, groups are labeled separately to avoid mixing methods, and maxMeasurements is described as bounding only the most recent stored sample rather than the whole period. The remaining gap is it does not explain the dateBasis semantics or what an empty result set looks like structurally.

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-loaded with purpose and scope, then caveats and return shape, with essentially no filler sentences. It is dense and telegraphic, however, and some clauses ('Groups questions, locales, identities, models, methods and web-search settings separately') read as a list dump rather than structured guidance.

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?

No output schema exists, yet the description supplies the return contract: recommended/known-decision and mention/known-mention counts, sample rates, pending/unavailable/unknown counts, and the grouping dimensions. Combined with the truncation and unknown-vs-zero caveats, an agent has what it needs to call and interpret this tool 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 0%, so the description carries the burden. It clarifies dateRange as inclusive UTC dates, ties sourceKind to the two source populations, and explains maxMeasurements as a bound on the most recent stored sample (with the truncation caveat). It says nothing about dateBasis ('observed_at' vs 'created_at'), so one of four parameters remains undocumented in both places.

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?

Names a specific verb and resource ('Summarize existing tenant-bound API probes... human ChatGPT observations'), and the phrase 'no provider call or model charge' plus 'existing' separates it from the measure/record siblings without needing to name them. An agent can tell this is a read-only aggregation over already-stored samples.

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?

Gives clear operating context: read-only marketing:read scope, inclusive UTC dates, and an explicit warning to check 'truncated' and 'wholeStoredPeriod' before treating a result as a period total. It also flags the interpretation rule 'No samples means unknown, not zero visibility.' It stops short of naming an explicit alternative (e.g., history or measure) or stating 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.