Capture batch

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

The description discloses important behavioral semantics beyond the annotations: near-identical claims are skipped rather than duplicated, superseding archives the old claim instead of deleting it, frozen-claim contradictions are parked for human review, and the operation is append-only. This goes well beyond the annotations, which only indicate mutation and non-idempotence, and directly shapes how an agent should reason about effects.

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 adds operational value: purpose, usage guidance, reconciler semantics, safety guarantee, and prerequisite. It front-loads the core action and differentiator before explaining behavior. No filler undermines the message.

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?

The description covers prerequisites, batching rationale, side-effect behavior, and safety boundaries, making the tool callable with good judgment. The main gap is that it does not describe the return/response shape, especially per-operation outcomes like applied, skipped, parked, or rejected. Given no output schema, a brief note about what the call returns would make it fully complete.

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?

The input schema already covers all parameters at 100%, so the baseline is 3. The description adds useful context beyond the schema, such as the dedupe-skip behavior, the append-only guarantee, and the need to call resume_context first to resolve ids and frozen states. It does not repeat parameter syntax, which is appropriate given the schema's richness.

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 action ('Apply a BATCH of claim operations'), a resource ('claim operations'), and a process ('through the reconciler'). It also distinguishes itself from sibling record_* calls by emphasizing batch scope. The title alone is vague, but the description resolves that ambiguity completely.

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 explicitly says to prefer this over several record_* calls when a turn produced more than one thing, giving a clear selection criterion. It also provides a prerequisite: call resume_context first so the agent knows existing ids and frozen claims. This is actionable, concrete guidance.

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