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

Adds substantive context beyond the annotations: no spending approval, separate purchasing approval remains mandatory, and no supplier dispatch or stock changes. That clarifies the blast radius of a non-read-only, non-destructive write in a way the hints alone cannot. It does not address idempotency behavior or how to recover from a duplicate submission, leaving a small 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?

Front-loaded with the trigger condition, then the conditional behavior, then the guardrails — a sensible order with no filler. The middle clause is dense and slightly hard to parse on first read ('using verified part price if your purchase-request approval preference is off').

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?

Covers the approval and side-effect story well for a mutation tool, and annotations plus the explicit negatives make the safety profile clear. But with no output schema and zero parameter descriptions, an agent still cannot tell what it gets back (a draft ID? a status?) or what to supply for idempotencyKey and rationale.

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% across 5 parameters, so the description must carry the burden — and it does not. It never explains partId, quantity, rationale, or the UUID idempotencyKey, nor what expectedApprovalRequired toggles. At best 'verified part' and 'approval preference' obliquely gesture at two of the five fields.

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?

States a specific verb and resource ('creating a pending purchase request'), constrained to 'a verified part', and immediately negates the wrong interpretation ('this never approves spending'). Against a sibling set of draft_* tools, the resource being drafted (a purchase requisition vs. a work order or vendor message) is unmistakable.

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?

Gives an explicit conditional: use this when the approval preference is off, otherwise prepare a proposal for review. That is real when-to-use guidance rather than implied. It stops short of naming or excluding siblings (e.g., draft_vendor_communication for supplier contact), so it is not a full 5.

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