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

With no annotations, the description carries the full burden and does add real context: the upstream source (data.police.uk), the spatial radius, the aggregation granularity, and the credit cost. It omits what happens when no crimes are recorded for the point/month, whether coverage is limited to England and Wales, and whether results are anonymised or snapped to approximate locations — meaningful gaps for a data-provenance tool.

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?

A single dense sentence that front-loads the primary purpose and appends the source, output shape, and cost without wasted words. Every clause carries information an agent needs.

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?

There is no output schema, so the description must characterize return values, and it does so compactly ('counts by category and a sample'). Given a simple four-parameter lookup, this is close to sufficient; the missing pieces are location-pairing rules and no-data behavior rather than any structural gap.

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 100%, but the schema descriptions are placeholders ('number', 'string', 'YYYY-MM'), so the description's 'point or postcode' phrasing is what tells the agent that latitude/longitude and postcode are alternative ways to specify the location. It does not state that these are mutually exclusive or that one pair must be supplied, and all four parameters are marked optional with no stated defaults, so the pairing rules remain inferential.

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?

States a specific verb/resource (street-level crime), the spatial scope (within about a mile of a point or postcode), the temporal scope (for a month), and the shape of the result (counts by category plus a sample). This is precise enough to separate it from sibling police_neighbourhood, which covers a different granularity, though the description never names that sibling to make the distinction explicit.

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?

The 'within about a mile of a point or postcode' clause implies when the tool fits, and the '(cost: 2 credits)' note signals it is a paid call worth using deliberately. There is no explicit when-to-use, when-not-to-use, or alternative routing (e.g., to police_neighbourhood or geocode) guidance.

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