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

Beyond the readOnlyHint and idempotentHint annotations, the description explicitly says 'Read-only — signs nothing', enumerates the exact data returned, and discloses pricing, auth requirements ('No wallet or API key required'), and free-tier availability. This gives agents concrete expectations for invocation and side effects.

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 somewhat long but front-loaded with the core purpose and backs it with essential operational details like pricing and auth. Each segment adds value; only the pricing clause feels slightly verbose relative to the technical core, but it is still useful for an agent deciding whether to call.

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?

Given the output schema exists and the annotations cover safety, the description supplies all necessary operational context: what data is read, that it is read-only, required input, pricing model, free tier, and absence of auth prerequisites. An agent can correctly select and invoke this tool without missing critical information.

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% for both 'address' and 'owner', so the baseline is 3. The description adds meaningful context by explaining the nonce's purpose ('so the signed payload can't be rejected/replayed') and clarifying 'Required input: address', which helps an agent understand why each parameter exists and which is mandatory.

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 clearly states the tool reads ERC-2612 permit data for B20 tokens, naming the exact resources: DOMAIN_SEPARATOR, owner nonce, and EIP-712 domain/type struct. It uses 'Read-only' and 'signs nothing' to distinguish from approval transactions, making the purpose unmistakable even among many b20_* 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?

The description provides clear context: the tool is for gasless-approval readiness and for building valid permits via signature instead of a transaction. It does not explicitly name alternative tools or state when-not-to-use conditions, but the intended scenario is well implied.

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