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

Annotations only declare readOnly=false, destructive=false, openWorld=false; the description adds the auth requirement (approver role), the human-confirmation gate, and a clear side-effect boundary ('Does not auto-approve, send, or wire'). It does not describe behavior on version conflict or what is returned, so it is not fully transparent.

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 core action and precondition are front-loaded, but the text is telegraphic and partly repetitive: 'Does not auto-approve' and 'A person still decides' assert the same idea, and 'Compact-10 APPROVED' is unexplained jargon. Trimming the final sentence would lose nothing.

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 non-read-only mutation with no output schema, the description covers authorization and the confirmation gate well, which is the most important context. It omits idempotency, conflict/retry handling for expectedVersion, and what a successful record produces, leaving an agent under-informed about failure modes.

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?

At 50% schema coverage, caseId and outcome are undocumented in the schema, and the description only names them rather than explaining format or constraints. The 'after confirmed true' phrasing reinforces the confirmed parameter's meaning. expectedVersion (optimistic concurrency) is never mentioned anywhere, leaving a real gap.

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 ('Record approve, refer, or decline' as a credit decision) and ties it to the signed-in approver, which separates it from prepare_decision and stage_term_sheet. It does not explicitly name a sibling as the wrong alternative, so it stops short of a 5.

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 real preconditions: only after 'confirmed true', only by a named human holding the approver role, and explicitly not an auto-approval path. The clause 'Compact-10 APPROVED still needs a staged term sheet' hints at sequencing with stage_term_sheet but is too terse to be a clean when-to-use rule.

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