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

No annotations are provided, so the description carries the full behavioral burden. It usefully discloses that no private key or RPC is required and that no transaction is broadcast, and it clarifies the meaning of a pending status. It still does not mention required permissions or the access_token, but it covers the most important non-obvious behavioral traits.

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 short sentences, each earning its place. The core read-only nature is front-loaded, followed by a useful operational constraint and a critical pending-status instruction. There is no filler.

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 three required, undocumented parameters, no output schema, and no annotations, the description is incomplete. It covers key behavioral points about non-broadcasting and pending handling, but it says nothing about input meaning, authentication details, or what the signed credit note return looks like.

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 does not mention any of the three required parameters (run_id, step_id, access_token). It adds no meaning, format expectations, or constraints beyond the bare schema names.

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 ('Read') and resource ('saved cash-refund status and signed credit note') and explicitly distinguishes this from a broadcasting operation ('without broadcasting a transaction'). It does not name a sibling tool directly, but the contrast with pipeline_refund is clear enough.

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 important in-state guidance ('Pending means resume the same refund, never send a replacement transfer'), which tells the agent what to do when status is pending. However, it does not state when to use this tool versus pipeline_refund, pipeline_refund_prepare, or pipeline_status, so broader usage context remains implied.

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