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

Annotations only mark it as a non-read-only, non-idempotent, closed-world write. The description adds real context beyond that: the counter is limited to one per offer, the amount is seller-chosen, the buyer's floor stays private, and the call is free. It does not say what the seller sees on success or what happens to the original offer, which keeps it out of 5 territory.

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 WHEN condition and constraint, then cost and privacy notes, then a compact example. The leading 'Barter counter.' is redundant with the name and title, and the example largely duplicates a fully described schema, but neither bloats the text.

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 4-parameter write with no output schema and only minimal annotations, the definition covers trigger, one-per-offer limit, pricing, and privacy. Missing only post-call behavior (whether the buyer is notified, what the response contains) and failure modes, which are secondary for a well-scoped mutation.

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 description coverage is 100%, so offer_id, counter_usd, key and note are already documented. The description reinforces that counter_usd is seller-chosen and that offer_id must be an existing buyer offer, but adds no format, bounds, or accepted-type detail beyond the schema. Baseline 3 applies.

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 definition names a specific verb and resource: the seller counters an existing buyer offer on their own listing. The opening fragment 'Barter counter.' merely restates the name, but the WHEN clause immediately supplies the discriminating detail (seller role, existing buyer offer) that separates it from accept/cancel siblings.

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 gives an explicit trigger condition — 'WHEN: seller counters an existing buyer offer on their listing' — plus a cardinality rule ('once per offer') that tells the agent when this call is no longer valid. It stops short of naming an alternative such as barter_accept or barter_cancel for the cases where countering is not the right move.

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