get_arrest_data

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

No annotations are provided, so the description carries the full burden. It does disclose genuinely useful behavior: the aggregate default ('yearly', summing monthly), that it only applies to data_type='counts', and that incomplete years are flagged in a top-level '_partial_years' key with unweighted rate averaging. It omits any mention of permissions, rate limits, or error conditions, leaving real gaps for a query tool with no annotation coverage.

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?

A one-line summary is front-loaded above an Args list in which each entry adds distinct value (formats, examples, conditional requirements). It is verbose but not padded; nearly every clause earns its place, though the argument list is long enough that it could be tightened slightly.

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?

An output schema exists, so return-value documentation is largely unnecessary, and the description instead explains the one non-obvious output feature ('_partial_years'). For a nine-parameter, five-required query tool with no annotations, coverage of inputs and aggregation behavior is solid, with only permission/error context missing.

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 0%, so the description must compensate, and it largely does: it documents all nine parameters with formats and examples ('mm-yyyy', offense codes like '11'/'30'/'150', level values, data_type 'counts'/'totals', category values, aggregate semantics). A few semantics remain thin (e.g., the 'sex' vs 'race' category distinction, valid level/category enumerations), but far more meaning is added than the bare schema provides.

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?

Starts with a specific verb and resource: 'Get arrest statistics by offense, optionally broken down by demographics.' The scope (offense-level arrest counts, optional demographic breakdown) is clear enough to separate it from siblings like get_nibrs_data or get_hate_crime_data. It does not, however, explicitly name or contrast against any sibling, so it stops short of a 5.

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 routes the agent to a sibling for offense codes ('Use get_reference_data with data_type="offenses" ...'), which is a concrete usage instruction, and it states when state/ori are required. But there is no guidance on when to choose this tool over other crime-data siblings (e.g., get_summarized_crime_data, get_crime_trends), so usage is implied rather than fully specified.

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