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

Annotations already declare readOnly, idempotent, non-destructive, but the description adds the behavior that actually matters: only APPROVED policies are returned, drafts and rejected are excluded, an empty list means nothing published rather than no obligations, and it warns against inventing rules. That is genuine disclosure beyond the hint set.

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?

Three tight sentences, front-loaded with the routing condition and followed by output semantics and the permission requirement. Slightly dense but no sentence is filler; the only lost point is that parameter guidance is absent rather than over-explained.

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 explain the shape of the result (approved-only list, empty-list meaning) and the auth requirement, which is the important part. However, for a 3-parameter filter tool with zero schema documentation, the caller still cannot know what to put in domain or framework, leaving a real gap.

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?

All three parameters (domain, framework, include_retired) have 0% schema description coverage and the description says nothing about them — no expected values, no format for domain/framework, no clarification of what include_retired actually toggles. The only related statement, "returns only APPROVED policies; drafts and rejected never appear", arguably leaves an agent unsure how retired policies interact with that filter.

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 and resource (find/list the approved policy to run a regulatory check) and grounds it with a concrete example (EU CBAM). It explicitly names the sibling it is not (ofp_policies for Open Footprint sector rules), so an agent can route without opening either schema.

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?

Gives a positive trigger (user needs data checked against a regulation), an explicit exclusion with the alternative named ("Do not use for Open Footprint sector rules; use ofp_policies"), and the prerequisite scope (compliance:read). Nothing about when-to-use is left to inference.

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