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

Goes well beyond the annotations: it discloses the full lifecycle (stored, auto-matched by job + country, human-reviewed before forwarding, nothing emailed automatically) and the private status_url/access key the caller must retain. That is exactly the operational context an agent needs and cannot infer from readOnlyHint/destructiveHint/openWorldHint.

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-loads the consent precondition and the matching/review behavior, then the return contract, in a tight two-sentence block. The sentences are long and clause-chained via semicolons, which costs a little readability but wastes no words.

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 20-parameter write tool, the description covers the consent gate, matching logic, human review, test mode, and handoff to get_rfq_status; the output schema already documents the return shape, so no further return-value detail is needed. Nothing critical to calling it correctly is missing.

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?

The description adds real meaning for two parameters — it explains why 'job' and 'country' matter (they drive matching) and clarifies test-mode behavior — but roughly half the 20 parameters (budgets, dates, contact fields, use_case_id, agent_name) get no treatment in the description or schema. With 50% schema coverage, this is adequate but leaves gaps.

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 (submit a request for quotes) and immediately narrows the scope with the consent=true precondition and 'real buyer' qualifier. It is clearly distinct from siblings like get_rfq_status and get_rfq_template, which are named as the follow-up and the field-source respectively.

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 explicit preconditions (buyer must be real and have consented) and a clear opting signal for non-production use ('Use test=true for testing'), plus routing to get_rfq_status for follow-up. It stops short of stating when NOT to submit, e.g. what to do if consent is absent.

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