fbi_hate_crime

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds context by stating that results are broken down by specific dimensions and that bias filtering is optional meaningful behavioral detail. It does not disclose potential response format limitations, pagination, or data availability, but with annotations covering the main safety aspects, a score of 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?

The description is three sentences with no filler. The core action and scope are front-loaded ('Get hate crime data...'), followed by a compact list of return dimensions, and then a helpful note on bias filtering. Every sentence earns its place, and the structure is easy to scan.

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?

For a tool with 6 optional parameters and no output schema, the description provides a reasonable overview but leaves some gaps. It does not explain the 'counts' vs 'totals' type parameter (though the schema describes it) or indicate default year ranges. Since no output schema exists, the description could more explicitly state the nature of the returned data (e.g., counts as numbers), but it does list the breakdown categories, which helps an agent understand what to expect. Moderate completeness.

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 100%, so the baseline is 3. The description goes beyond the schema by explaining the significance of the bias parameter with concrete examples ('12'=Anti-Black, '14'=Anti-Jewish, etc.) and clarifying that it is optional. This adds meaningful semantic value for selecting parameter values, particularly for the bias enum, which the schema only lists as codes without context.

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 clearly states the tool's purpose: 'Get hate crime data from the FBI at national, state, or agency level.' It specifies the resource (FBI hate crime data) and the verb (get), and provides concrete details about the returned breakdowns (bias category, offense type, victim type, offender demographics, location type), making it distinct from sibling FBI tools.

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 implies usage: if an agent needs hate crime data, this is the tool, and it can be scoped to national, state, or agency level. However, it does not explicitly state when to choose this over alternatives like fbi_crime_summarized or fbi_nibrs, nor does it mention any exclusions or prerequisites. The usage context is clear from the subject matter but not directly articulated.

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