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

Goes well beyond the annotations, which only declare non-read-only, non-idempotent, non-destructive, closed-world. The description discloses hard rate limits (three per caller, one per caller/business pair, eight per business), content-refusal rules for phone numbers, emails and links, and the crucial non-delivery caveat that this call sends nothing and forwarding is at most weekly with no guaranteed reply.

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 action and return value in the first clause, then orders preconditions, contact rules, refusals, limits, and delivery caveats logically. It is dense and long, but each sentence carries a distinct rule; a little more line-breaking or bolding of the limits would help scanning.

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 non-idempotent write tool with no output schema and undocumented parameters, this describes preconditions, payload hygiene, refusal conditions, quota limits, delivery semantics, and even the agent's user-facing framing ('never say the business has been contacted'). Nothing an agent needs to call it safely and truthfully 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?

With 0% schema description coverage across 6 parameters, the description compensates almost fully: it defines consent as affirmative shopper approval, marks share_contact as a separate explicit choice, and instructs omitting first_name/reply_email when contact is not shared, while the question constraints (no phone/email/links) are stated. Only minor gaps remain, such as the 3-500 character bounds and the UUID format for business_id.

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 ('Queue an unanswered question') plus the return shape ('returns status and message'), and the precondition naming ask_business makes clear it is not the same as asking a question directly. An agent can distinguish it from ask_business without opening the schema.

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 gating: call only after ask_business returns answered: false and the shopper approves the exact question and business, with consent: true at that point. It also gives an exclusion path for contact data ('omit name/email otherwise') and names the alternative behavior (suggest direct contact) rather than leaving it to inference.

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