List recent claims

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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint, openWorldHint). The description adds genuinely useful behavioral context beyond that: result ordering, per-claim fields returned, workspace scoping, and the next_cursor pagination contract. No contradiction with annotations; 'Lists' matches readOnlyHint=true.

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 sentences with zero waste: purpose and scope first, then filters, then pagination. Every sentence earns its place and the most decision-relevant information (what the tool lists and returns) is front-loaded.

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 6-parameter, 0-required tool with no output schema, the description covers the essential surface: scope, ordering, returned per-claim fields, filter options, and pagination mechanics. The remaining gaps — the undefined semantics of action and agent_id — are the main reason it isn't a 5, but the rich annotations and clear filter/fetch narrative make it adequate for correct invocation.

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 only 33% (just limit and cursor have descriptions), so the description must compensate. It does helpfully enumerate the filter set and clarifies state's allowed values (queued or decided) and cursor's role ('Paginate with the returned next_cursor'). However, action and agent_id remain semantically opaque — what actions exist and what agent_id refers to is left undefined.

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 and resource ('Lists claims'), scopes it to the API key's workspace, and adds ordering ('newest first') plus the returned fields (state, verdict, receipt_id). This makes it clearly distinguishable from siblings like get_verdict, get_receipt, and verify_receipt, which operate on single entities, and submit_claim, which creates.

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 filter list and pagination instruction imply the usage context, but the description never explicitly says when to prefer this tool over alternatives or when not to use it. With siblings like get_verdict and get_receipt available, no routing guidance is provided — the agent must infer the boundary between listing and fetching a single entity.

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