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

With no annotations, the description carries the full burden and does disclose meaningful traits: 'This moves no money' (despite the refund name) and the hard security constraint 'never send a private key.' It still omits what state preparation creates (reservation, expiry, idempotency) and what the seller-approval flow requires of the caller afterward.

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?

Four short sentences, front-loaded with the core action, each carrying distinct information (what it does, that no money moves, the auth requirement, the prerequisites). No filler or restatement of the name.

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?

Covers the safety profile and preconditions well, which is the critical part, but with no output schema and no annotations it should also signal what preparation yields and how to proceed (the follow-on pipeline_refund call). That workflow context is absent.

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 0% and the description says nothing about run_id, step_id, or access_token. The run_id pattern ('^paid_...') in the schema hints at format, but the description does not explain that run_id identifies the finished pipeline run, that step_id must be a verified paid step, or how access_token relates to the caller.

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+resource+scope: 'Prepare a cash refund for a verified paid step of a finished pipeline,' and clarifies it is a preparation step, not the execution. It does not, however, name the sibling it is distinguished from (pipeline_refund / pipeline_refund_status), so an agent must infer the routing rather than being told.

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?

Provides real preconditions ('seller must approve the authorization locally', 'refunds require seller cooperation and a configured gas sponsor'), which implies when the call can succeed. But it never states when to use this versus pipeline_refund or pipeline_refund_status, nor the ordering of the refund workflow, so the routing guidance is only implied.

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