Reserve Purchase Requisition

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

The destructiveHint: true annotation signals this tool has side effects (consuming/reserving funds). The description adds relevant context by noting approval is 'independently approved' and unavailable from the agent surface, which helps set expectations. However, it doesn't explain what 'reserve' does concretely—whether it's reversible, whether settlement follows, or what happens to unspent reserves. The 'single-use' qualifier adds some value beyond the annotation.

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 sentences with zero waste. It front-loads the core purpose and adds one critical constraint (approval unavailable from agent surface). Every word 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?

This is a financial mutation tool with destructiveHint=true, 7 parameters, and no output schema, yet the description is only two sentences. It doesn't explain reserve lifecycle (does settlement follow?), TTL semantics, idempotency guarantees, failure behavior when funds are insufficient, or whether reserve is irreversible. For a money-moving operation this is notably under-specified. The sibling set includes settle and reconcile tools, suggesting a multi-step lifecycle that the description doesn't help navigate.

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 the description must compensate for 7 undocumented parameters. The description clarifies nothing about individual parameters—amountUsd, vendor, purpose, sourceMessageId, requisitionId, ttlMs, and idempotencyKey all rely purely on their names. However, several parameter names are reasonably self-explanatory (amountUsd, vendor, purpose), and the idempotencyKey hints at retry semantics. The ttlMs field meaning (time-to-live presumably) is left entirely implicit.

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 a specific verb+resource structure ('Reserve a single-use amount from an independently approved purchase requisition'), which clearly distinguishes it from siblings like create_purchase_requisition, list_purchase_requisitions, and settle_purchase_requisition. The scope is identifiable from the siblings, though the term 'reserve' could use more context about what reserving vs settling means operationally.

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 states that 'Approval is unavailable from the agent tool surface,' which is a useful exclusion note, but it doesn't explain when this tool should be used versus create/settle/list purchase requisition tools. There's no guidance on prerequisites (an approved requisition must exist first, presumably via create_purchase_requisition), no idempotency guidance, and no mention of when alternatives would be appropriate.

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