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

Annotations already mark this as non-read-only, non-destructive, non-idempotent, and open-world. The description adds the critical behavior that this is only a build step and does not sign/submit/confirm, which prevents dangerous misinterpretation as a transaction execution tool.

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 tight sentences, front-loaded with the core action followed by the critical non-actions and the caller requirement. Every sentence adds distinct value.

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 covers purpose and the non-signing nature, which is important given the annotations and no output schema. However, for a 7-parameter tool with a nested quote object and no output schema, it does not explain the return format, authentication needs, or several required parameters.

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 43%, so the description must compensate, but it only restates the quote and from bindings already documented in the schema. It gives no additional meaning for side, chain, token, or slippageBps.

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 verb (Build) and resource (unsigned swap transaction material), plus the endpoint and the binding to a prior quote and from address. This distinguishes it from sibling quote tools and from any signing/submission tool.

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?

Implies the tool must be used after a prior quote and with a public from address, and explicitly says it does not authorize, sign, submit or confirm. However, it does not name the alternative (e.g., memeswap_quote) or state when not to use it.

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