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

The annotations already establish that this is not a read-only operation, that it is idempotent, and that it is not destructive. The description adds genuinely useful behavior: the quote is prepared asynchronously and emailed with a payment link, a best_effort delivery is shorter and not refunded, and polling must be scheduled rather than looped. It does not say what happens when expected_revision does not match, which is the main remaining behavioral 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?

The description is front-loaded with the core action, followed by the conditional probe_below_target branch and then the async follow-up flow. Each sentence carries operational information. It is dense and a little long, but nothing is clearly wasted.

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 state-changing confirmation and quoting step with four required parameters, 0% schema coverage, and no output schema. The description covers the workflow and the async side effects well, but leaves the parameter contract and revision-mismatch behavior unexplained, which is a significant gap for a tool that locks an immutable sample scope.

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 has to carry the full burden of explaining the parameters, and it does not. It only implies sample_id and expected_revision; request_id, request_capability, and idempotency_key are never mentioned, and request_capability in particular is completely opaque. The idempotency_key length bounds and the 32-character minimum are also left 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 uses a specific verb and resource: confirm the current immutable sample_id and revision, then request a fixed quote. That is clear enough for an agent to act on. However, it never distinguishes this tool from the sibling confirm_quote, so an agent facing both cannot tell which one actually locks in the quote.

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?

It gives concrete guidance: check sample_rows.probe_below_target and, if true, tell the person the source_estimate and offer to broaden keywords before confirming. It also says to check get_request on a schedule and never in a loop, and to use start_order or create_order afterwards. What is missing is an explicit statement of when to choose this tool over confirm_quote.

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