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

Annotations already declare readOnly, idempotent, non-destructive behavior, and the description goes well beyond that: it discloses ownership scoping (only the caller who ran it can read it), the not-found response for another account's id, and the required compliance:read scope. These are exactly the auth and error semantics an agent needs and cannot get from the 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?

Two sentences, use-case first, then access and error constraints. No redundant restatement of the title or annotations, and every clause adds information.

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 one-parameter read tool with full annotations, the description covers when to call, permission requirements, and error behavior. The one gap is the return shape, which is undocumented since no output schema exists, so an agent cannot anticipate the evaluation fields returned.

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 0% and the single parameter has no description, so the description carries the burden; it explains that the id identifies a previously run evaluation rather than an arbitrary record. It does not state the UUID format, but that is visible in the schema itself.

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 pair (retrieve or audit) and a specific resource (a previous regulatory evaluation) keyed by id. The word 'previous' implicitly separates it from compliance_evaluate, which produces a new result, though that sibling is never named outright.

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 a clear triggering condition ('when a user wants to retrieve or audit a previous regulatory evaluation') and states the access prerequisite (compliance:read). What is missing is an explicit pointer to compliance_evaluate for running a fresh evaluation, so the when-not side is only implied.

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