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

Adds substantial behavior beyond annotations: no recording or binding, works even when offers are disabled, requires a Last Price credential with price compute scope, and rejects sandbox keys with a 403 until a person claims the workspace. These are exactly the side-effect, prerequisite, and error signals an agent needs.

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?

Three sentences, front-loaded with the core dry-run purpose, then the no-side-effects guarantee, then prerequisites. Every sentence contributes actionable information with no repetition.

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?

With no output schema, the description explains the return shape (accept/counter/reject plus limits) and covers setup requirements and error conditions. Nothing material for correct invocation 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?

Schema coverage is 100% and all four parameters are documented in the schema itself. The description does not add parameter-level detail (e.g., round semantics or previous_counter usage) beyond what the schema already provides, so baseline 3 is appropriate.

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 dry-run action against the user's own product and describes the exact result (accept, counter, reject) with limits. The phrase 'Nothing is recorded and nobody is bound' distinguishes it from the real offer sibling without needing to name 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?

Gives clear conditions for use: 'so you can check your terms first' and 'works while offers are off', plus credential and claimed-workspace prerequisites. It does not explicitly name the alternative real-offer tool (make_offer), but the dry-run framing makes the intended context clear.

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