fbi_arrest_data

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

Annotations declare readOnlyHint=true, and the description aligns by stating 'Get arrest statistics' without implying mutation. The description adds useful domain context: offense codes are numeric and includes specific examples, plus 'all' for all offenses. It also discloses that returns are 'counts or totals' broken down by year, age, sex, race, ethnicity, which is valuable behavioral context beyond the annotation. It doesn't cover pagination or rate limits, but for a read-only stats tool with a clear annotation, this is solid.

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 two sentences, front-loaded with the core purpose, and efficiently packs offense code examples and output dimensions without redundancy. Every clause adds value; no filler or repetition of schema details.

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?

Given the tool's complexity (6 params, 48 offense enum values, levels: national/state/agency) and no output schema, the description provides a strong overview: data source, levels, offense codes, and returned breakdowns. It doesn't enumerate all 48 offense codes (schema covers that) but gives enough examples to make the tool usable. It lacks exit conditions like date-range default values, but the schema covers defaults, and the description is complete for an agent to invoke with confidence.

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% (all 6 parameters have descriptions), so the schema already documents each parameter thoroughly. The description adds a bit of meaning by explaining offense codes are numeric with examples and the 'all' option, which complements the schema's enum list. However, it doesn't add substantial info beyond the schema's own descriptions for parameters like from_year/to_year defaults, which the schema also covers. Baseline 3 is appropriate because schema does the heavy lifting.

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 gets arrest statistics from the FBI at national, state, or agency level, with a specific verb ('Get arrest statistics') and resource ('FBI'). It names the three coverage levels and the output dimensions (counts/totals by year, age, sex, race, ethnicity), distinguishing it from sibling tools like fbi_crime_summarized and fbi_hate_crime.

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 when to use the tool (for arrest statistics at national/state/agency level) and hints at data granularity, but it doesn't explicitly explain when not to use it or name alternative tools like fbi_crime_summarized or fbi_nibrs. The context is clear enough for an agent to select this tool for arrest-specific data, but it lacks explicit exclusions.

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