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

Annotations only declare readOnlyHint=false and destructiveHint=true; the description adds the state machine, the irreversibility of the outbound email ('cannot be recalled'), the contactEmail prerequisite, the fact that the email body carries the order rather than the PO PDF, and that the order becomes uneditable afterwards. These are consequential side effects an agent could not infer from structured fields.

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 imperative ('Place the order') and every sentence carries an operational instruction or a hazard warning. The all-caps emphasis and the repetition of the ask-before-emailing rule consume space, but they are safety-relevant rather than filler.

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 destructive, irreversible, no-output-schema mutation tool, the description covers preconditions, side effects, irreversibility, failure mode (missing contactEmail), and post-action state. An agent has everything needed to call it correctly and to explain the outcome to the merchant.

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 both parameters are already documented, including the default and the 'ONLY after the merchant said to send it' guard. The description nonetheless adds decision criteria the schema lacks (phone/in-person/portal cases for false, and what happens when no contactEmail exists), plus the warning that purchaseOrderId is an id from get_purchase_orders, not a PO number.

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 ('Place the order') and pins the exact state transition (draft/suggested → sent), which no sibling name conveys. It is immediately distinguishable from hub_update_purchase_order, hub_receive_purchase_order and hub_cancel_purchase_order, which the description even names as the only remaining post-send actions.

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?

Explicit when-to-use (order must be draft/suggested), when-not (sendEmail:false for phone, in-person, or supplier-portal orders), a mandatory precondition (ask the merchant every time), and a blocking prerequisite (contactEmail must exist on the supplier). Alternatives after sending are named. Nothing is left to inference.

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