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

Adds real context beyond annotations: no signature verification, the token is not stored, results must not be used for trust decisions, and per-call billing explains why repeats are not free (consistent with idempotentHint=false). The sentence 'Reads or computes only and changes nothing' duplicates readOnlyHint/destructiveHint rather than adding value, and error behavior on malformed tokens is unstated.

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-loads the operation and its outputs, then stacks cautions, example, and pricing in a sensible order. The pricing/credits sentence is long and partly boilerplate, though it does justify the non-idempotent charge behavior.

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?

No output schema exists, and the description compensates by describing decoded header/payload plus date-normalized claims and an expiry verdict. Missing only failure behavior (malformed or non-JWT input) and whether the output is structured or stringified.

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?

Single required parameter with 100% schema coverage, so the schema baseline applies; the description only adds a worked example token, which helps confirm the expected compact-serialization format but no other semantics. Baseline 3 is right.

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?

Specific verb+resource: 'Decode a JSON Web Token's header and payload without verifying the signature', and it enumerates the outputs (iat/nbf/exp as dates, expired flag). This clearly separates it from generic siblings like base64_decode and json_format.

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?

Explicit when-to-use ('Use to debug auth flows') and a strong when-not warning ('Do not use the result to trust a token'). It does not name a sibling alternative, but no JWT verification tool exists among the siblings, so the routing gap is small.

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