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

Annotations only declare safety flags (readOnlyHint=false, idempotentHint=false), so the description carries the real behavioral burden and does so richly: response varies by whether seller.answers_questions is true, price negotiation may yield a deal valid 24 hours for one request_order, a 24-hour price hold, decline reason codes (declined, slow_down, handoff, email_required, conversation_stopped), three-declines-per-conversation cutoff, and per-minute/per-day rate limits. It also warns that a seller's reply to an escalated question does not come back through this tool.

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 core purpose and the sibling distinction are front-loaded, and nearly every clause carries unique operational information (rate limits, deal terms, stop conditions). However, it is a dense single block mixing behavioral rules, error reasons, and negotiation mechanics without structural separation, which makes it harder to scan than it needs to be.

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?

An output schema exists, yet the description still maps the meaningful response shapes an agent must branch on — inline answer, deal object, 'seller answers in chat,' and the terminal reason codes. For a non-idempotent tool with negotiation and rate-limit side effects, nothing critical to correct invocation appears 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?

Schema coverage is 100%, so the baseline is 3, but the description adds operational meaning: conversation_id exists so 'Ego sees the earlier questions and answers,' and it ties deal.id forward to request_order. It does not restate the offer_id sourcing rule (already in schema) or the 500-character limit, but the added conversational continuity semantics justify going above baseline.

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?

Opens with a specific verb and resource — 'Ask one question about a listing' — and immediately scopes what questions are appropriate (availability, condition, timing, location, sizes, delivery/pickup). It also names the sibling it is not: 'To send your question to the seller as your user instead, use message_seller,' so an agent can distinguish it from message_seller without opening either 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?

Explicitly frames the use case as pre-decision ('before your user decides') and gives a concrete follow-up rule: pass conversation_id 'for a follow-up about the same listing.' It also names the alternative path (message_seller) and its selecting condition, plus the branch where the seller has no Ego assistant and 'answers in chat.'

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