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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds genuinely useful non-annotation context — free, no key required, and a default freshness window of 90 days — which tells the agent there is no auth setup or cost barrier. It does not disclose response shape or whether the 90-day/1 km figures are fixed defaults versus overridable by parameters.

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?

Three short sentences, front-loaded with what the tool returns and followed by access conditions and a usage tip. Almost every phrase carries information; 'before reading too much into a low count' is informal but actionable. Slight ambiguity around the 1 km/90 day figures costs it the top score.

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 and six mostly optional parameters, the description should say more about what a coverage response contains — the mention of agencies, record types and freshness is a good start but leaves the shape and units unclear. Annotations carry the safety profile, so the remaining gap is mainly about return values and parameter interaction.

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 50%, with lat, lon and address the only documented properties. The description clarifies that location is a point and hints at a spatial cutoff ('within 1 km') and a temporal cutoff ('last 90 days'), which gives meaning to radius_m and the from/to pair. It does not resolve precedence between address and lat/lon, nor explain what from/to accept, so a meaningful part of the six-parameter surface remains unaddressed.

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 and returns: which police agencies publish records near a point, which record types, and how fresh they are. That is far more than a restatement of the title 'Data coverage', and it distinguishes the tool from siblings like nearby_incidents (actual records) by framing it as a source-availability check. It stops short of a crisp single verb, reading more as a list of questions the tool answers.

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?

'Use it before reading too much into a low count' gives a real usage cue: treat this as a diagnostic step when results look sparse. However, it does not name an alternative sibling or state when NOT to use it (e.g. when you already know the agency coverage, or when you want incident counts rather than publication metadata). Guidance is implied rather than explicit.

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