Citywide crime statistics

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=true, so the safety profile is fully covered by structured data. The description adds the aggregation semantics (grouped counts) which is useful, but it does not disclose return shape, pagination behavior, or default ordering. With annotations carrying the behavioral load, a 3 is appropriate.

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?

Two tight sentences with zero filler. The grouping dimensions are front-loaded, and the usage example is presented compactly as a follow-on cue. Every clause earns its place.

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?

An output schema exists, so the description need not explain return values, and annotations cover safety. The description is largely complete for a 5-param, no-required aggregation tool. The one gap is not naming the sibling it overlaps with (get_crime_near), which would help an agent choose 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 80%, so the schema already documents most parameters (year, limit, offense, patrol_division) including examples. The description adds value by explicitly tying group_by='year' to the offense filter as a combined pattern (trend analysis), which is semantic meaning not present in the schema's enum alone. It does not cover 'place_type' or 'clearance_status' but those are self-explanatory enums.

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 verb (summarize) and resource (citywide CMPD incident counts) with the grouping dimensions enumerated. However, it does not distinguish itself from the sibling get_crime_near, which also deals with crime data. The agent can tell this is an aggregation/count tool, but the boundary against the 'near' variant is left implicit.

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 description gives one concrete usage pattern ('group_by=year with an offense filter for trends'), which is helpful implied guidance. But it does not state when to use summarize_crime over get_crime_near or the generic summarize_dataset, and no exclusions or prerequisites are given.

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