update_rejections_in

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

The description adds behavioral context beyond the annotations: it explicitly says 'replacing its item lines and narration', which clarifies destructive action beyond the annotations' destructiveHint. It further mentions matching/collision caveats, pointing to further potential quirks. These directly complement the structured data (readOnlyHint=false, destructiveHint=true) without contradictions.

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 two compact sentences with no filler. The main purpose is front-loaded, and the subsequent sentence includes two cross-references to related sibling definitions that append useful constraints without redundant detail. Every sentence earns its place.

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?

Given that the tool is part of a large, well-defined sibling family and that the description relies on two existing siblings for field lists and caveats, the description is complete enough for an agent to locate the missing information. The lack of an output schema is offset by the tool's purpose and the explicit statements about what fields are used. There is no mention of authorization or error conditions, but those are generally not necessary for a complete description.

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 all parameters are described in the input JSON schema. The description adds that the item field replaces all existing lines and that voucherNumber identifies the existing voucher, matching the schema's own description. It references create_rejections_in for field set, but does not add unique parameter-level insight beyond what the schema already provides.

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 the action as 'Update an existing Rejections In voucher', specifies the resource (TallyPrime voucher) and the effects (replacing item lines and narration). It differentiates from siblings by noting the addition of voucherNumber versus create_rejections_in and by the resource being Rejections In, not Rejections Out or Material In.

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 implies usage: use this tool when updating an existing Rejections In voucher, not when creating one (since it references create_rejections_in). It does not explicitly provide when-not conditions or rule out alternatives, but the distinction is clear. The reference to 'same matching/collision caveats as update_material_in' partially communicates the use context and recourses, but the caveats themselves are not clarified in this description.

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