get_area_history

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

Annotations already declare readOnlyHint and openWorldHint, so safety is covered; the description adds meaningful non-obvious behavior beyond them, namely that results are historical aggregates rather than a crash database and that durations and counts are included. It omits any mention of result volume, aggregation edge cases (e.g. a location with no history), or how the look-back interacts with the 2026-07-12 history start, which caps it below 5.

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 leads with the core behavior, then usage examples, then a data-provenance caveat — a sensible front-loaded order with little waste. The quoted example questions are slightly verbose for what they convey, but they earn their place by disambiguating the use case.

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 carries the burden of describing returns, and it does so reasonably: counts by hour and weekday, common incident types, and typical duration. It does not describe the shape of the response or how sparse/no-data areas are represented, which an agent would want when interpreting results.

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 75%, and the description reinforces the key semantics: it frames the result as scoped to 'within the radius' and existing schema text explains place handling, saved places, and that center overrides place. The only untouched parameter is radius_km, which has no schema description at all, leaving its unit and default meaning unstated anywhere.

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 states a specific resource and aggregation: incidents and closures within a radius, bucketed by local hour and weekday, with incident types and typical durations. It also clarifies the data provenance ('counts CommuteScout saw in official feeds, not a crash database'), which separates it from a raw incident feed like get_incidents. It never names the sibling tools it differs from, keeping this just 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 explicit usage contexts with quoted example questions ('is this intersection bad at rush hour', 'when is it quietest around the stadium'), which tells the agent the intended pattern-analysis use case. It does not state when not to use it or point at alternative tools such as best_time_to_go or get_incidents, so routing between siblings is left to inference.

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