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

Despite annotations already covering the safety profile, the description adds substantial behavior: no network access, nothing stored or logged, keys/secrets not echoed, error shape (422 for malformed tokens and JWEs, not charged), latency (<0.1s), and pricing/quota. This is well beyond what the annotations convey. The only minor tension is openWorldHint=true alongside 'no network access,' but this is not a safety contradiction.

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 core decode/no-verify distinction and generally dense and useful. However, the 'not verified' point is restated twice ('without verifying it' and 'Decoding does not verify the signature'), and the trailing pricing/free-tier/docs block adds bulk, so it is slightly redundant for its length.

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?

An output schema exists, yet the description still sketches the return shape (header/payload split, alg/typ/kid, iat/nbf/exp as ISO 8601, expired/not_yet_valid flags) and the error condition. Combined with annotations, an agent has everything needed to call and interpret 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?

Schema description coverage is 100% and the single 'token' parameter is fully documented there, including the accepted leading 'Bearer ' form. The description adds no parameter-level syntax or format detail beyond the schema, so the baseline of 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?

States a specific verb (decode) and resource (JWT), immediately scopes it as 'without verifying it,' and names the sibling verify_jwt as the contrasting tool. An agent can distinguish it from verify_jwt and decode_calldata without opening any schema.

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?

Explicitly routes: 'To check the signature use verify_jwt' and reinforces that 'the result is untrusted until verify_jwt passes.' The condition separating decode from verify is stated outright rather than implied.

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