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

Annotations already mark it read-only and non-destructive; the description adds the critical behavioral boundary, 'Returns unsigned calls; never signs or submits.' This goes beyond the annotations by telling the agent the tool never produces a signed transaction or broadcasts anything on chain.

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 description is two tight sentences: one states the operation and scope, the next states the key safety boundary. Everything present is necessary, and the most identifying information is front-loaded.

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 a full input schema and an output schema present, the description supplies everything else needed: the exact on-chain function, the mainnet context, the one-offer scope, and the no-sign/no-submit guarantee. There is no missing context that would cause an agent to misinvoke it.

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?

The input schema already documents both parameters completely, with 100% coverage, so the baseline is 3. The description adds minimal new parameter meaning beyond confirming they identify one mainnet offer, which is reasonable but not a major supplement.

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 names the exact function cancelOffer(), the resource ('one mainnet offer'), and the network context ('mainnet'). This clearly distinguishes it from internal-marketplace prepare tools and related listing/accept/buy operations.

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 description clearly scopes this to a mainnet offer, which is enough to choose it over prepare_internal_cancel_offer. It does not explicitly mention alternatives or exclusions, but the mainnet/one-offer scope is strong and immediately usable.

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