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

Annotations only declare readOnlyHint=false, so the description carries the burden and does well: it discloses the 7-day lock, the extension of an existing 24-hour hold to 7 days, inventory deduction on 'complete', and which party may invoke each action. It does not say whether cancel is reversible, what happens to an existing lock on cancel, or whether calls are idempotent.

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?

A single tight paragraph in 'label: meaning' form, front-loaded by action name with zero filler. It could add one lead-in clause stating that this is the deal state-transition endpoint, but nothing present is redundant.

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 mutation tool with real consequences (inventory deduction, binding locks) and no output schema, the core action semantics are covered but several things an agent needs are not: the 'reason' parameter's purpose, what the tool returns, and post-cancel state. Adequate but with clear gaps given the schema's 40% coverage.

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 only 40%, but the description compensates for the most consequential parameter by defining all four 'action' enum values, which the schema lists bare. It reinforces 'body' (message to the counterparty on agree) but leaves 'reason' completely undefined in both schema and description, and only implies that 'deal_id' targets the deal.

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 description enumerates each of the four action values with the concrete state transition it performs (agree locks 7 days and closes; complete confirms and deducts inventory; cancel terminates), so an agent can see exactly what the tool does per call. It never frames the tool as a whole or distinguishes it from siblings such as counter_offer or buy_listing, which are the nearest alternatives.

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?

It effectively routes between the four actions, and even supplies a when-not condition for 'accept' (if negotiation already settled at 7 days, it isn't needed) plus a caller-eligibility rule for 'cancel' (either side may use it). It stops short of naming external alternatives like counter_offer or make_offer, so an agent still has to infer when to abandon this tool entirely.

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