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

Annotations already declare the safe, idempotent, read-only profile, so the description is free to add domain context: the data is a bounded self-hosted snapshot, it covers crimes known to law enforcement only, and it carries provenance and coverage metadata. These are useful behavioral/trait disclosures beyond the annotations, though no auth or rate-limit detail is given.

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?

Three sentences, front-loaded with the core purpose, followed by fields and then usage/caveats. Every sentence carries weight, though it is on the denser end and could trim some enumerations.

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?

With no output schema, the description compensates by enumerating the returned fields (offenses, clearances, rates per 100,000, populations, coverage percentage, pagination, provenance) and stating the data-scope caveat. For a 7-param, no-output-schema tool this is complete enough to call 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 100%, so all seven parameters (including the YYYY-MM formats, the enum, and the overlap note on aggregate categories) are already documented. The description adds 'bounded' and 'one state and one offense' framing but no new parameter syntax or format meaning, so baseline 3 is correct.

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?

States a specific verb (Return), the exact resource (bounded monthly trend for one state and one FBI summarized UCR offense category), and the data source (LiveDataLink self-hosted CDE snapshot). This clearly differentiates it from siblings like fbi_cde_national_crime_trend, fbi_cde_compare_state_to_national, and fbi_cde_state_month_snapshot without needing to open a schema.

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?

Provides concrete use-case examples ('California violent-crime trend in 2023', 'monthly motor vehicle theft reported in Texas') and an explicit exclusion ('never use for cross-state rankings or individual decisions'). It does not name a specific alternative sibling to redirect to, so it falls just short of the top band.

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