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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, covering the safety profile. The description adds that it checks exp/nbf claims and that the key format depends on algorithm, which is useful context. However, it does not disclose failure behavior (e.g., invalid signature or expired token) or what the tool returns, which would be expected for a verification 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?

Two sentences carry all essential information: purpose with algorithm list, claim checks, parameter selection, and the alternative tool. The most important usage constraint is front-loaded, and there is no filler or redundant text.

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?

For a verification tool with no output schema, the description should explain what result the agent can expect (e.g., boolean, error, or success indication). It also does not mention edge cases like exp/nbf failure handling. While the usage guidance is strong, the absence of return behavior and error semantics leaves a gap for correct invocation and interpretation.

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%, so the baseline is 3. The description goes further by explaining the relationship between algorithms and parameters (HS* needs secret, RS/PS/ES need JWK or JWKS URL), and the token schema description already echoes the alternative to jwt_decode. This adds value beyond the schema's individual field descriptions.

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 opens with a specific verb ('verifies') and resource ('JWT signature'), enumerates supported algorithms and claim checks, and explicitly distinguishes from jwt_decode by stating it is for when authenticity matters. This makes its purpose unmistakable and differentiates it from the sibling decode 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?

The description explicitly names jwt_decode as the alternative and conditions the choice on whether authenticity matters. It also gives concrete parameter selection guidance: 'Provide a secret for HS*, or a JWK or JWKS URL for RS/PS/ES.' This leaves no ambiguity about when and how to invoke the tool.

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