Resolve claim

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

Even though annotations already mark destructiveHint=true and readOnlyHint=false, the description adds substantial behavioral detail: 'Nothing is deleted; closing archives,' accept 'superseding whatever it conflicted with,' reject turns the claim into a guardrail 'so it is never re-proposed,' and accepting against a FROZEN claim is 'refused rather than silently overriding.' This goes well beyond what the annotations convey and clarifies the exact nature of the destructive action.

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 description is dense but every sentence earns its place. It uses 'Two uses' as a clear structural marker, front-loads the core action, and then covers each call pattern, the mandatory reason, archival behavior, and the frozen-claim caveat without fluff. The length is justified by the tool's real complexity.

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 tool with two call patterns, a three-value enum, and a frozen-claim edge case, the description is complete. It covers accept, reject, and close, explains the mandatory reason, states that nothing is deleted, and specifies when unfreeze is required. Since all parameter details are in the schema and there is no output schema, nothing an agent needs to invoke this correctly is missing.

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 description coverage is 100%, with all five parameters already documented, so the baseline is 3. The description reinforces that reason is mandatory and that unfreeze requires explicit user consent, but it does not add parameter-level meaning beyond what the input schema already provides. It correctly emphasizes the reason's purpose for future sessions, but that is contextual rather than new parameter semantics.

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 opens with a specific verb and resource: 'Close a claim, recording WHY.' It then enumerates two distinct uses — parked claims (accept/reject) and open risks/questions/actions (close) — which clearly separates it from siblings like record_rejection, record_open, and freeze_claim. This is far beyond a tautology and gives an agent a precise mental model.

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?

The description gives explicit when-to-use guidance: parked needs_review claims take accept or reject, while dealt-with open items take close. It also adds an exclusion ('accept applies only to a parked claim') and a frozen-claim precondition requiring the user's go-ahead. However, it never names sibling tools as alternatives, so an agent must infer when record_decision or record_rejection would be more appropriate.

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