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

With no annotations the description carries the full behavioral burden and does reasonably well: it discloses the returned report structure, the temporal coverage limit, the data provenance/ethics caveat ('public data: no victim or suspect identities, not evidence of guilt'), and the per-call cost of 5 credits. It omits whether the call is strictly read-only, auth requirements, and what happens when no match is found.

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?

The core lookup action is front-loaded in the first sentence, followed by three tightly packed sentences covering output, coverage limits, disclaimers and cost. Every sentence carries information; nothing is restated from the schema or title.

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, and the description does describe the returned report well enough (pinpointed location, public details, candidate matches, ranked similar incidents, area pattern summary). For a 12-parameter tool with zero required fields it still leaves the 'at least one selector required' rule and the no-result behavior unspecified.

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%, so several parameters (similar_limit, similar_radius_m, search_radius_m, lat/lon) have no inline documentation. The description compensates by naming the accepted search selectors and by explaining that the date is used 'plus or minus a window' and that similarity ranking draws on same offence, location type, time of day, block and proximity – which effectively explains the similar_* and radius parameters.

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?

Specific verb+resource: pinpoint a past Chicago crime incident by case number, date, block, type, keyword or coordinates, then rank similar incidents. It is plainly distinguishable from siblings like crime_map_data and crime_stats because it is incident-level lookup rather than aggregate or map data, and the title reinforces the 'exact case + similar cases' scope.

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 clear context on what selectors are accepted and bounds the data range ('2001 to about a week ago'), which is real usage guidance. It does not name alternatives or state when NOT to use it, and with 0 required parameters it never says that at least one locator (case, date, block, keyword, coords) must be supplied – a meaningful omission for a 12-param tool.

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