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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, and the description reinforces and extends them: no session/order/payment created, no suppliers contacted, and URLs are never fetched (important given openWorldHint). It also discloses the two possible response shapes — clarifications requested or a ready brief with digest — plus that the output is private JSON for the buyer to import.

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 sentences, front-loaded with the purpose, with no filler wording. The density is high but each sentence adds a distinct fact (scope, preservation, response form, exclusions); it is only slightly compressed for readability.

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 complex nested-input tool with no output schema, the description adequately covers the behavioral contract (no side effects, two response outcomes, URL non-fetching) and points implicitly at the import workflow. The gap is the data model: many nested fields remain unexplained, though the schema itself directs callers to discover_rfq_basic_v0 for the canonical reference shape.

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 a single deeply nested 'draft' parameter at 0% schema description coverage, the description must carry the load; it does map several key fields (source references, must-match specs, buyer budget/policy) and adds the constraint that references are text/URL only and assets are excluded. However, roughly a dozen nested subfields (matchPolicy, conflict_resolutions, default_retention_reference_ids, destinationPort, many buyer_policy keys) receive no semantic guidance 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 first sentence names a specific verb (Prepare) and resource (China sourcing requirement / Verified RFQ Basic) and states it is free. The closing sentence enumerates what it does NOT do (no session, order, payment, supplier contact, or paid sourcing), which separates it from the paid siblings in the set. It does not explicitly distinguish itself from discover_rfq_basic_v0, the closest sibling, which keeps it below a 5.

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?

Usage context is clear: use it to draft/validate a requirement for the free Basic RFQ flow, then import the returned JSON into the existing form to review, confirm and pay separately. The negative list carves out the paid/transactional path. It stops short of an explicit 'use X instead when Y' routing statement.

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