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

Annotations already cover read-only, idempotent, and non-destructive behavior. The description adds substantial value beyond that: the verbatim-source caveat ('GDC's wording verbatim', 'narrative is GDC's own text'), the data provenance and volume, and notably the naming/redaction behavior ('Structured rows name staff, officers and contract staff as GDC printed them; other people appear by category and role only'). These are exactly the kind of behavioral traits an agent cannot infer from annotations alone.

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 dense but each sentence earns its place: source/scope first, then row structure, then filters with examples, then the naming caveat. It is a single block rather than segmented, but the logical flow is strong and there is no filler or repetition of what annotations already state.

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 read-only tool with eight optional parameters and no output schema, the description covers the dataset, row granularity, fields present, filter options, and a behavioral caveat about naming. The gaps are pagination behavior for page/per_page and explicit semantics of default values (empty string and 0 meaning no filter). Given the complexity of the tool, the description is close to complete but not exhaustive.

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 carries the full burden—and it largely succeeds. Six of eight parameters get meaningful semantics with concrete examples: facility slug (dooly-state-prison), actor_category with the full enum, item_category with examples, arrest_made with a yes|no|unstated enum, year, and q as text match. Only page and per_page are left to inference, and their meaning is self-evident; default-value semantics (e.g., year=0 meaning 'all years') are not spelled out.

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 states a specific verb and resource: retrieving incident-level rows from GDC's published contraband arrest reports. It adds precise scope (2016-present, ~960 incidents, one row per incident) and enumerates the fields carried, making the tool's purpose unambiguous and distinguishable from an aggregate or stats tool.

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 clearly conveys what the tool returns (incident-level detail with filters) and thus implies when it applies, but it never explicitly says when to prefer it over alternatives. In particular, the sibling get_contraband_summary is a natural candidate for aggregate queries, yet no routing guidance is provided. Filters are listed, so an agent can infer usage, but exclusions and alternatives are left unstated.

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