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

Annotations already communicate readOnlyHint and destructiveHint, so the bar is lower. The description adds valuable context beyond annotations: the approval is bounded and WETH only moves on acceptance. This clarifies the behavioral distinction between preparing an offer and settling it, which is useful for an agent deciding whether this step is safe.

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?

Two sentences, front-loaded with the primary action and scope, followed by the key safety-relevant caveat. There is no filler or repetition of schema content.

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?

The description, schema, annotations, and output schema together give an agent enough to understand what the tool does, which marketplace it targets, and when it is safe to call. A small gap is that it does not explicitly name mainnet alternatives or state that the tool merely returns a prepared transaction rather than executing it, though the readOnly annotation already signals this.

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 has 100% description coverage for all four parameters, so the description does not need to restate them. It adds no parameter-level detail beyond what the schema gives, so the baseline score of 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?

The description uses a specific verb-resource pair—'Prepare bounded WETH approval and makeOffer()'—and scopes it to the NFH-owned Sepolia internal marketplace. This clearly separates it from sibling tools like prepare_internal_buy, prepare_internal_accept_offer, and the mainnet-marketplace prepare variants.

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 gives clear context: this is the preparation path for a WETH offer on the internal marketplace, and WETH only moves on acceptance. It does not explicitly name alternatives or exclusion conditions, but the market scope and action type are clear enough to guide selection among many similar prepare_* siblings.

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