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

Adds real behavioral context beyond the annotations: the secret is used only for this call and is not persisted, and no API key or account is required. It also discloses that decode validates exp, nbf and iat, which the schema does not state. The readOnly/idempotent annotations remain consistent since no state is stored.

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 tool's purpose and then the mode semantics. The closing 'No API key, no account and no sign up' sentence is slightly redundant with the preceding 'secret is not stored' claim, but still conveys the auth-free calling model.

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 no output schema, the description covers return values by naming them ('answers jwt' and 'answers decoded_payload'), plus the auth model and the per-call secret handling. An agent has everything needed to call either mode correctly.

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 50% (token and payload documented, secret and operation not), so the description must compensate. It does so by defining what each operation does and which parameter belongs to which mode, adding the timestamp-claim semantics for decode that the schema omits.

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 and resource ('Create or check an HS256 JSON Web Token') and spells out both modes: encode signs a payload, decode verifies a token. This distinguishes it clearly from computational siblings like hash_data, encode_data and verify_hash, which operate on different primitives.

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 encode/decode split and the 'decode only'/'encode only' parameter roles imply when each mode applies, and the token expiry claims (exp, nbf, iat) hint at verification use. However, there is no explicit when-to-use/when-not guidance or routing to a sibling tool for adjacent tasks such as hashing or signing non-JWT data.

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