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

Adds substantial behavior beyond the readOnly/idempotent annotations: zeros are included for every CDE category, groupings are tallied separately and their totals can differ (so one grouping cannot substitute for another), and unrecognized state/ORI values silently return zeros. That last point is a real trap the agent would otherwise fall into.

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?

Five sentences, each carrying distinct load: what is returned, the grouping-total caveat, the scope/identifier mapping, and the zero-ambiguity warning. Lead sentence establishes resource and time range before drilling into caveats; no filler.

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 an 8-parameter, multi-scope aggregation tool this covers everything an agent needs: scope requirements, date semantics, offense narrowing, and the two caveats (differing grouping totals, silent zeros) that would otherwise cause misinterpretation. An output schema exists, so return shape needs no explanation.

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 100%, so baseline is 3; the description earns above that by noting the offense parameter narrows results, tying each scope to its one permitted identifier, and warning that bad state_abbr/ori values yield zeros rather than errors — meaning that goes beyond the schema.

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?

Opens with a specific verb+resource: arrest counts reported to FBI CDE, scoped to nation/state/agency over a monthly window, with named breakdowns (offense, sex, race, age group). The resource is clearly distinct from siblings like fbi_get_crime_estimates or fbi_get_hate_crimes, and fbi_search_agencies is named as the ORI lookup path.

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?

Gives concrete scoping rules (national omits identifiers, state needs only state_abbr, agency needs only ori) and routes the agent to fbi_search_agencies for the ORI. It does not explicitly say when to prefer this over sibling datasets such as crime estimates, but the context is unambiguous.

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