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

Beyond the annotations, it discloses critical behavior an agent could not otherwise know: consumption commits before the response is returned, so a dropped response is unrecoverable, and decryption must happen locally with the key never sent to the server. This directly reinforces and extends destructiveHint and idempotentHint=false with operational consequences.

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 most important fact, destructive consumption, is front-loaded, and the retry warning is tight and actionable. The trailing 'No API key, no account and no sign up' does not help an agent decide or invoke correctly and is the one expendable clause.

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?

With no output schema, the description correctly states that ciphertext is returned and must be decrypted locally, which is the essential return contract. It omits the ciphertext encoding/algorithm details, but the irreversibility warning and local-decryption requirement cover the highest-risk unknowns for a 2-parameter destructive 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 description coverage is 100%, including formats and what each credential means, so the baseline is 3. The description mentions 'the read token' but adds no format or validation detail beyond the schema; 'No API key, no account and no sign up' is onboarding copy, not parameter meaning.

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: 'Destructively consume and return ciphertext using the read token.' The 'destructive' framing implicitly separates it from read_one_time_secret_receipt, but no sibling is named explicitly, so an agent must infer that burn_one_time_secret is different.

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?

'Reveal only with explicit intent; never automatically retry' gives a clear use condition and an explicit prohibition. It stops short of naming alternatives (e.g., burn_one_time_secret or receipt reading) or stating what to do when a caller lacks the token.

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