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

Adds context beyond annotations: it discloses that plaintext is 'sensitive' and gated on explicit user intent, which is meaningful behavioral guidance for a decrypt operation. Annotations mark openWorldHint=true and readOnlyHint=false but don't convey the user-consent gate; this adds real value, though it doesn't describe failure modes or rate limits.

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 tight sentences, action first then behavioral constraint. No filler, and the important gating caveat is front-loaded enough to be noticed.

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, so the description should ideally note that plaintext is returned (it does mention 'Returns sensitive plaintext'), which helps. However it omits error behavior, what happens if confirm_decryption is false, and doesn't cover the pubkey/ciphertext parameter roles fully. Adequate but with gaps for a security-sensitive tool.

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 33%, so the description must compensate. It explains the purpose of confirm_decryption indirectly via 'explicit user intent' but doesn't clarify that this must be set to true, nor does it explain the pubkey or ciphertext parameters beyond what the schema's types imply. Baseline adjusted for partial coverage.

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 (decrypt), resource (NIP-44 ciphertext), and mechanism (paired signer). Distinguishes from nip44_encrypt by naming the decrypt direction. Doesn't distinguish from sign_event-type siblings beyond the crypto operation, but the NIP-44 reference is specific enough.

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 phrase 'only after explicit user intent' implies a precondition for use, which is useful. But it doesn't name alternatives or specify when-not to call, and offers no guidance on how the confirm_decryption flag interacts with the caller's workflow beyond the implied 'ask the user first'.

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