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

With annotations covering the safety profile, the description adds real behavioral context: it discloses the three possible outcome states, that the seller's rules answer on the seller's behalf, and that an agreed price carries an approval_url. It does not say what happens when the price exceeds 'the person's limit' (rejection vs. error) and does not reconcile the non-idempotent annotation with the idempotency_key parameter.

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-loaded with the action, then the routing rules, then the role caveat. The next_action explanation is slightly redundant with the output schema and the parenthetical '(your last price again is fine)' makes one sentence run long, but no sentence is filler.

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 usefully summarizes what next_action values mean and where approval_url lives, which is exactly the context an agent needs before choosing between countering and accepting. The remaining gap is error/limit-exceeded behavior for a tool that mutates a live negotiation.

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 meaning the schema lacks: price_usd must stay within 'the person's limit' and may legitimately repeat the previous price. That constraint on the price value is not encoded anywhere in the schema.

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 gives a specific verb and resource (answer a seller counter with a new price) and the role rule ('Only the buyer's agent counters: the seller's rules answer for the seller') separates this from market_make_offer / market_ask_seller. It stops short of naming any sibling tool explicitly, so an agent must infer the boundary rather than read it.

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?

The next_action branches are spelled out as concrete usage instructions: counter_again means come back with another counter inside the limit (repeating the last price is acceptable), decide_on_last_price means the ask is final, send_approval_url means the price is agreed. That is strong 'when to call again' guidance, but it never says when to stop and hand off to market_accept or market_request_approval instead.

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