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

Goes well beyond the annotations (which only declare read-only/idempotent/closed-world) by disclosing the rego_unavailable: source_not_retained fallback, the fact that a policy without Rego is not loaded into the engine, the meaning of the enforcement field, and the required compliance:read scope. These are exactly the behavioral details 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?

Four tight sentences, each adding distinct value: use condition, return semantics, fallback behavior, and authorization requirement. The use condition and the key caveat are front-loaded and nothing is repeated from annotations or schema.

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 and no annotation detail, the description supplies the return payload (rules, provenance, coverage, Rego, enforcement) and the degraded-path marker, which is substantial. It leaves the exact response shape and the source of the id unclear, but an agent has enough to call it 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?

Only one parameter (id, uuid) with 0% schema description coverage, so the description must carry meaning. It establishes the parameter selects exactly one approved policy, but never says the id is the policy identifier or where it comes from. Partial compensation, not full.

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?

States a specific verb+resource: retrieve the full rules, provenance and coverage of one approved regulatory policy. That distinguishes it from the plural listing sibling compliance_policies and from compliance_evaluate, though neither sibling is named explicitly. An agent can tell this is a single-policy detail fetch, not an evaluation or a list.

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?

Opens with an explicit selection condition ('Use this when you need the full rules, provenance and coverage of one approved regulatory policy') and adds a behavioral guardrail ('Do not reconstruct the Rego'). It does not name alternatives or state when NOT to use it (e.g., use compliance_policies to browse, compliance_evaluate to run), 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.