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

The annotations already declare destructiveHint=true and idempotentHint=true, so 'Repeating a burn is safe' largely restates them. What the description adds beyond the structured fields is the authentication profile ('No API key, no account') and the precise boundary of what is destroyed (pending ciphertext only; already-revealed secrets are unaffected). That last point is the key behavioral fact an agent needs before calling a destructive 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?

The destructive action and its consequence are front-loaded in the first sentence, and the remaining sentences each add a distinct fact (idempotency, scope limit, no-auth). The trailing marketing-style phrasing 'no account and no sign up' is slightly redundant with 'No API key' but still conveys auth requirements.

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 two-parameter destructive tool with full annotation and schema coverage and no output schema, the description covers the essential facts: what is removed, that repeats are harmless, that revealed secrets are out of reach, and that no credentials are needed. It does not describe the response or what happens if the token is invalid, but annotations and schema carry most of that weight.

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%, and both parameters carry regex patterns and semantic notes ('not a credential', 'cannot reveal'). The description only echoes that the receipt token is the means of burning, adding no format or failure-mode detail beyond the schema, so baseline 3 applies.

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 states a specific verb and resource: 'Permanently remove any pending ciphertext'. It also scopes the operation to pending ciphertext, which implicitly separates it from reveal_one_time_secret. It never names a sibling tool explicitly, so it stops short of a 5.

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?

'Burning cannot recover or revoke ciphertext already revealed' tells the agent the operation only applies to pending secrets, and 'Repeating a burn is safe' covers repeat calls. However, it never points to reveal_one_time_secret or read_one_time_secret_receipt as the alternative when the agent actually wants to read the secret, which is the most likely competing intent.

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