receipts_refund

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

Beyond annotations (destructiveHint=false, idempotentHint=false), the description discloses auto-issuance, refundOf linkage, inherited series, and the accumulating multiple-partial-refund behavior until quantities are exhausted. It omits permission/auth requirements, but adds substantial behavioral context.

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?

Front-loaded with the core behavior, then constraints. Dense but every sentence (linkage, series inheritance, preconditions, lineSelections branching) carries information; 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 3-param mutation tool with no output schema and reasonable annotations, the description covers mechanics, preconditions, and partial-refund semantics. Return shape is left implicit, which is the only notable gap.

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 100% so the baseline is 3, but the description adds real meaning: it clarifies that lineSelections with partial quantities is allowed and that repeated partials can be issued against the same parent until exhausted. This goes beyond the schema's per-line note.

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 and resource ('Issue a refund (counter-)receipt') and immediately explains the mechanism: mirrors parent with negative quantities and inverted amounts. This clearly separates it from receipts_issue and receipts_cancel.

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?

Gives concrete preconditions (parent must be issued and not itself a refund) and explicit branching on lineSelections (omit for full refund, pass for partial). It does not route to an explicit alternative sibling, but the usage conditions are clear.

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