receipts_refund

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It discloses key behaviors: the refund is auto-issued, linked back via refundOf, and inherits parent receipt series. It also states constraints (parent must be issued and not itself a refund). It doesn't explicitly mention side-effects like whether the parent's status changes or if payments get altered, but given the auto-issued/linked/inherits detail, it covers the most material behavioral aspects reasonably well.

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 a single dense paragraph that packs substantial information without waste. It front-loads the core action ('Issue a refund counter-receipt') then layers constraints and usage modes. Every sentence earns its place. It's slightly long and could arguably be broken into shorter sentences, but nothing is redundant or 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-parameter tool with 100% schema coverage and no output schema, the description is complete. It explains the refund semantics (negative quantities, inverted payments), the linkage (refundOf), series inheritance, full vs partial refund modes, and quantity-exhaustion limits. Nothing critical appears missing for an agent to select and invoke this tool correctly. It doesn't explain return values, but no output schema exists so this is a minor gap at most.

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%, and the schema already documents all 3 parameters well (uuid as parent receipt, companyId override, lineSelections with quantities). The description adds value beyond the schema by explaining the semantic difference between passing lineSelections (partial/lines-specific refund) versus omitting it (full refund of whole receipt), and notes that partial quantities are supported. This supplements the schema's mechanical descriptions with business semantics.

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 clearly states what the tool does: 'Issue a refund (counter-)receipt' that mirrors the parent receipt with negative quantities and inverted payment amounts. It specifies the resource (receipt), the action (refund), and the mechanism (counter-receipt with negative quantities). It distinguishes itself from sibling receipt tools like receipts_create, receipts_issue, receipts_cancel by describing the specific refund behavior.

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 provides explicit when-to-use context: 'Parent must be issued and not itself a refund.' It also explains the two usage modes clearly: omit lineSelections for full receipt refund, or pass it to refund only specific lines. It even discloses constraints like 'Multiple partial refunds against the same parent are allowed until the original quantities are exhausted,' which is strong usage guidance.

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