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

Annotations only cover read-only/idempotent/closed-world, so the description carries the real behavioral load and does: up to 3 ranked candidates, a ~25,000-word English word list, the letter key, the open letters, and a high/medium/low confidence with reason. It also discloses degraded conditions (short texts, names, rare words lower confidence, and the tool says so) — exactly the kind of context annotations cannot express.

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-loaded with the trigger, then outputs, then parameter guidance, then limits — a sensible order with no filler. It is a single very long run-on sentence with many clauses, which slightly hurts scannability.

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?

Even though an output schema exists, the description still conveys what the agent needs to interpret and relay results (candidates, key, open letters, confidence). Coverage of edge cases and scope limits makes the definition complete for a 3-parameter, single-sibling 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 100% and the schema already documents ciphertext and known_letters with examples, so the description's note about passing printed clues in known_letters largely restates structured data. allow_self_mapping is never mentioned in the description, though its schema entry is complete. Baseline 3 is correct.

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 ('suggest cryptogram solutions' framed as 'Use this when the user is stuck on a cryptogram') and explicitly names the artifact it consumes ('gives the enciphered text'). The one sibling, generate_cryptograms, is a generator, so the solving framing distinguishes it immediately.

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 an explicit trigger ('when the user is stuck... and gives the enciphered text') plus concrete exclusions: number or symbol ciphers, Caesar shifts with a shown key, and a newspaper puzzle without its text. It also instructs the agent to report confidence to the user, which is a usage rule, not just a capability statement.

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