propose_purchase

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

With no annotations, the description carries the full burden and does well: it discloses the outcome branching (APPROVE vs REJECT), the single-use nature of the approval_id, its 10-minute validity, and what a rejection returns (the refusing rule plus a hint). It does not state whether the call itself has side effects or how the approval_id is later consumed, leaving a residual gap.

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, and everything is front-loaded: the action and payload constraint come first, the outcome contract second. No sentence is redundant.

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 no-annotation, no-output-schema tool with a nested items array, the description covers the response contract well (APPROVE/REJECT, approval_id lifetime, rejection payload). The remaining gaps are the meaning of mission_id and how the returned approval_id ties into a subsequent order, which an agent would need to infer.

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, and it only partially does. It clarifies that 'items' carry SKUs and quantities, but says nothing about mission_id (the required scoping key) or the optional 500-character justification, leaving two of three parameters unexplained anywhere.

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 states a specific verb and resource: submitting a basket of SKUs/quantities to a 'deterministic gateway' for approval on behalf of a mission. This is clearly distinct in spirit from the write-oriented sibling place_order, but it never names or contrasts that sibling, so the agent must infer the ordering 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 says what is sent ('only SKUs and quantities') and what comes back, which implies a pre-order approval step, but it never states when to call this versus place_order or get_policy, nor any prerequisites such as a valid mission_id. Usage is implied rather than directed.

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