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

Annotations only declare it is a non-destructive open-world write. The description adds substantial behavior: what is created (a private conversation where price/timing get confirmed), what is explicitly NOT done (payment, stock hold, delivery booking), idempotency via an unchanged request_key on retries, and the privacy handling of reply_token.

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?

Four tight sentences with the precondition front-loaded and no filler. Density is high but almost every clause carries an operational rule; the opening fragment format is slightly abrupt but functional.

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 12-parameter write with no output schema and sparse schema descriptions, it covers preconditions, idempotency, side-effect boundaries, and the next step (ask_business with inquiry_id and reply_token, which implies the return values). Gaps remain around customer_authorized semantics and line-item composition.

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?

With only 17% schema coverage, the description carries the burden and does explain the highest-risk fields: expected_estimate_cents must mirror estimate_order's output, fulfillment must match what the business offers, and request_key has a length/randomness/retry contract. However, customer_authorized, the lines structure, and the zip/address delivery constraints are left to the schema or unexplained.

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 makes clear it submits an order request that opens a private conversation with the business, and names estimate_order as the source of catalog_revision/estimate. The verb is somewhat implicit ('Creates a private conversation') rather than stated head-on, but an agent can tell what gets created and why.

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 a hard precondition ('Only after the customer asks to order and approves the itemized estimate') plus the follow-up route to ask_business for replies. It also implicitly excludes payment flows with 'No payment, stock hold or delivery booking,' though it does not explicitly contrast with confirm_request or checkout_order.

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