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

Annotations carry only a title, so the description bears the full behavioral burden and does well: single attempt only, time-limited, and clear success/failure consequences (escape with the painting vs. jail). It leaves unstated whether a wrong answer is recoverable or whether the answer format matters, but the core risk profile is disclosed.

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?

Three short sentences, front-loaded with the action, then the precondition, then the stakes. The closing clause 'Right = you escape with the painting; wrong or too late = jail' conveys the risk compactly with zero filler.

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 exists, and the description covers the meaningful outcomes (escape with painting or jail) plus the one-shot timing constraint. For a simple two-parameter action tool this is nearly sufficient; only the exact response shape and answer-format expectations are left to inference.

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 50%: 'answer' is described generically as 'Your answer, as text' and heist_id has no schema description at all. The description implies heist_id comes from the preceding heist_attempt call, which adds some value, but it says nothing about answer format, casing, or whether the riddle text is needed.

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?

Names a specific verb and resource ('Answer the Gatekeeper GX-9000's challenge at the front door') and anchors it to a precise state returned by a named sibling, heist_attempt. An agent can distinguish this from heist_attempt, heist_bail, and heist_case without opening any schema.

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?

Explicitly states the triggering condition: call this only after heist_attempt returns outcome 'at_the_door'. It also warns 'One try, before the timer runs out', which tells the agent to prepare an answer first. It does not name heist_bail as the alternative path, which is the only real gap.

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