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

Annotations cover the safety profile (readOnly, idempotent, non-destructive), and the description adds substantial non-obvious behavior: the list is a current snapshot because DCH removes reinstated providers rather than flagging them, counts span the whole 1,300+ row list rather than a page, the source is keyless, and the counted date field (sanction_date / SANCDATE) is named. These are exactly the semantics an agent cannot infer from structured fields.

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 snapshot/coverage purpose is front-loaded and every clause carries real information (snapshot caveat, whole-list counting, date field name, source). It is a single dense paragraph with some redundancy between the coverage summary and the counting mode, but nothing is wasted.

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?

There is no output schema, yet the description names the metrics returned, clarifies that the response identifies which date field was counted, and explains the snapshot caveat that affects interpretation. An agent has everything needed to call it and read the result 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 coverage is 100%, so year, start_date and end_date are already fully documented, including YYYY-MM-DD formats and the 'ignored if start_date/end_date are given' precedence. The description only restates the year example and that counting is list-wide, adding marginal meaning beyond the schema — baseline 3 is appropriate.

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 resource (Georgia DCH OIG exclusion list coverage) and enumerates exactly what it reports: total exclusions, NPI count, distinct provider types, oldest/newest sanction date, plus an optional date-bucketed count mode. It is clearly separable from the sibling ga_medical_check_exclusion, which screens a specific provider rather than describing the dataset.

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?

It gives an explicit use case — verify the screening data is fresh enough before a compliance decision — and an explicit second use case with a sample question ('how many Georgia DCH OIG exclusions had a 2025 effective date'). It does not name the sibling check tool or say when this should be skipped, so it stops short of a 5.

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