bank_candidate

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

Annotations only provide readOnlyHint=false, idempotentHint=true, and destructiveHint=false. The description discloses far more: writes to a private sibling file, runs a written-and-reimported gate, replaces the filename only on PASS, deletes the candidate on FAIL, preserves existing output, and defers snapshot saving until after promotion. This is rich behavioral context beyond the annotations, with no contradiction.

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 description is dense but efficiently ordered: what it does, how it does it, failure behavior, snapshot behavior, return summary, and usage guidance. It is front-loaded with the core purpose, though the single long paragraph could be broken into shorter sentences for easier scanning.

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 complex atomic operation, coverage is strong: it details PASS/FAIL semantics, snapshot timing, preservation guarantees, return content, and when to prefer this tool over alternatives. The output schema covers return structure, so the description does not need to duplicate that. The main gap is object_name semantics and exact error scenarios, but overall it is sufficiently complete for selection and invocation.

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 0%, so the description must carry parameter meaning. It clarifies snapshot_name ('the geometry snapshot is saved only after promotion') and gives some meaning to filename ('replaces filename only on a fully verified PASS'). However, object_name is never explained, leaving one of the three parameters without semantic grounding.

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 opens with a specific verb-resource pair: 'Atomically promote a gate-clean STEP as the safe output/checkpoint.' It also explicitly contrasts itself with batching export() and save_snapshot(), so an agent can distinguish it from those siblings without opening the 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?

It explicitly states when to use the tool: 'Use this instead of batching export() and save_snapshot() for scored floors and final candidates.' This gives both a clear use case and the named alternatives, leaving little to inference.

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