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

Beyond the annotations, the description discloses that this is a write, that it is free, that refusal returns recorded:false with reason 'no_active_claim', and that the result is an opaque blob never parsed, indexed, or logged. It also adds auth details and the equivalent HTTP route, which annotations do not provide.

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 and logically ordered: action, exclusions, idempotency, refusal mode, result semantics, then auth. It loses a point because 'FREE' is repeated twice with nearly identical billing claims, adding mild redundancy.

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 still specifies the refusal result shape (recorded:false, reason 'no_active_claim') and makes the success path clear by saying a duplicate attempt receives the stored result. It also includes auth, HTTP route, and prerequisite claim context, so an agent has what it needs to invoke the tool correctly.

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 4 parameters, so the baseline is 3. The description adds meaning beyond the schema by tying key to the previously claimed key, clarifying that result is opaque, and explaining agent_key as a fallback for hosts that cannot set headers.

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 precise action: 'Attach the outcome to an idempotency CLAIM you hold'. It immediately differentiates from siblings with 'NOT for finishing a mailbox task (use inbox_ack) or a queue item (use work_done)'.

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?

It explicitly tells agents when to use it (after holding a claim, to store a result) and when not to, naming inbox_ack and work_done as alternatives. It also handles the failure path: re-claim the key first if the claim expired or was never held.

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