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

Annotations already establish readOnly, idempotent and non-destructive, and the description goes well beyond them: it discloses that counts are exact only for the units swept, that the response self-reports when it hit its cap, and that an empty findings list means 'nothing failed among the swept units' rather than compliance. That last caveat is exactly the misinterpretation risk an agent would otherwise fall into.

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 core action, and the capped-sweep and empty-result caveats are placed after the main statement where they matter. The four-question example sentence is long but each phrase maps to a distinct intent, so it earns its space; nothing is padded.

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 carries the burden of explaining return values and does so: findings list, per-finding unit counts, example units, and a cap indicator. Combined with 100% schema coverage of three optional parameters, an agent has enough to call this correctly without guessing.

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 pack, limit and status are already documented with defaults and a maximum in the schema. The description adds no parameter-level detail such as the effect of omitting pack or how status interacts with the sweep, so the baseline 3 applies.

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 first sentence names a specific verb and resource ('Sweep this organisation's units and report which regulatory checks are failing') and states the return shape: failing checks, affected unit counts, and examples to open. It is clearly distinct from single-unit tools like trace_unit or where_is, though it never names the nearest sibling (dpp_readiness) to sharpen the boundary.

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?

Quoted trigger questions ('which of my units have a broken custody chain', 'what will not pass on 18 February') give concrete when-to-use guidance that an agent can pattern-match against a user request. There are no explicit exclusions or named alternatives, so an agent must infer that per-unit or per-finding queries belong to siblings.

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