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

Goes well beyond the annotations, which only declare the write/non-idempotent/closed-world profile. The description adds TTL (24 hours), the one-time return of read and receipt tokens, the 100-per-IP-per-UTC-day rate limit, the 16384-byte pre-encryption plaintext cap, and a concrete security warning about client logging of arguments and bearer tokens.

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 verb and TTL, then layers the security instruction, the return-value note, the size limit, the rate limit and the auth model in short declarative sentences. No filler; every clause carries an operational constraint.

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?

There is no output schema, and the description compensates by stating that separate read and receipt tokens are returned exactly once. Combined with the rate limit, size cap, and no-account model, an agent has everything needed to call this correctly on the first attempt.

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 100%, so the nonce/version/algorithm/ciphertext fields are already documented. The description still contributes meaning the schema does not: the 16384-byte plaintext limit before encryption and the requirement that the key never accompanies the envelope, both of which constrain how the parameters must be produced.

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 ('Store an already encrypted AES-256-GCM envelope') plus a hard scope limit ('at most 24 hours'), which naturally separates it from reveal/burn/receipt siblings. It never names those siblings explicitly, so an agent must infer the routing from the verb alone.

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?

Gives clear operational prerequisites: 'Encrypt locally first. Never send plaintext or the decryption key to MCP, chat or this API.' It also flags the non-idempotent, rate-limited, unauthenticated nature of creation. What's missing is explicit direction to the companion tools (reveal_one_time_secret, read_one_time_secret_receipt, burn_one_time_secret) for the retrieval half of the flow.

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