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

Annotations already declare read-only, idempotent, non-destructive, non-open-world behavior, so the safety profile is covered. The description adds genuinely useful operational context beyond that: filtering happens server-side, rows are returned newest-year-first, results are paged, and `matched_offenses` reports what the offense filter matched.

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?

Front-loaded with the payload the tool returns, followed by compact parameter semantics and paging behavior. Every clause carries information; there is no filler or repetition of the name.

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 does the work of describing return content: the metric fields, `matched_offenses`, and the paging shape. It slightly underspecifies pagination boundaries (no maximum `limit`, no total-count signal), but an agent can call the tool correctly from what is given.

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 carry all five parameters, and it largely does: `offense` is a case-insensitive substring of the GDC offense name and also accepts a four-digit offense code; `year` is the release calendar year; `limit` (default 30) and `offset` page the rows; `summary_only` returns just the summary block. It also documents the empty-string default behavior for `offense`.

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 dataset and enumerates exactly what is measured: average sentence, years served, percentage served, parole-release share, lifer figures, and a trend summary. It is far more than a restatement of the name. It does not, however, explicitly distinguish itself from nearby siblings such as get_parole_statistics, which also covers parole-release information.

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?

Usage is implied rather than stated: the description explains that omitting `offense` yields the all-crimes series and that `year` scopes to release year, which tells the agent how to shape a call. But it never says when to choose this tool over alternatives like get_parole_statistics or get_system_statistics, and no exclusions are given.

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