Settle Purchase Requisition

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

The key disclosure 'Events are append-only' is valuable behavioral context beyond the destructiveHint annotation, informing the agent that operations are irreversible. The annotation already signals destructiveness, and description reinforces it without contradicting. No annotation contradiction detected.

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?

Two sentences, zero waste. Each sentence earns its place: first defines the dual action, second discloses the append-only invariant.

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?

With 6 parameters, 0% schema coverage, no output schema, and a destructiveHint annotation, the description is thin. It doesn't explain which parameters are required for each status branch (committed requires evidence+actualAmountUsd; released likely doesn't), the mutual exclusivity of the two actions, or the append-only consequence for callers. Sibling create/reserve/list tools suggest a lifecycle that isn't explained.

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%, so description carries the parameter burden. The description mentions 'receipt evidence' (mapping to evidence parameter) and 'actual spend' (mapping to actualAmountUsd), but doesn't clarify the relationship between status ('committed'/'released') and which parameters apply to each branch, or what reason/is used for.

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 uses specific verbs ('Commit actual spend', 'release an unused reservation') identifying two distinct actions coupled with 'receipt evidence'. It distinguishes the settle action from siblings like reserve_purchase_requisition and reconcile_purchase_ledger, though it could be clearer about the reconciliation relationship.

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 when to settle (commit with receipt evidence or release unused reservation) but doesn't explicitly state when NOT to use this vs siblings like reconcile_purchase_ledger or how it relates to reserve_purchase_requisition. No explicit exclusions or alternative tool names given.

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