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

Discloses that it persists the prediction and returns a call_id, which is a write operation. Lists all return items (calibrated_confidence, similar cases, etc.). No annotations exist, so the description carries the burden; it adequately covers behavior without contradictions.

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 sentences front-load the purpose, list returns, and end with a clear usage instruction. No redundant or unnecessary text.

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; description sufficiently explains what is returned (calibrated_confidence, cases, interval, Kelly stake, devil's-advocate, call_id). Mentions the feedback endpoint. Could elaborate on formats or examples, but core usage is covered.

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% with clear parameter descriptions. The tool description does not add new information beyond what the schema provides (e.g., domain 'filter similar cases', stakes 'compute kelly_stake'). Baseline of 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 clearly states the tool's action ('Calibrate a prediction's confidence against historical outcomes') and specifies the resource (prediction confidence). It distinguishes from siblings like batch_calibrate by detailing unique return values (Kelly stake, devil's-advocate counter-argument) and the feedback loop.

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?

Provides context on when to use: backed by Alya's resolved-outcomes ledger covering freelance proposals, prediction markets, and paper trading. Mentions the follow-up step (POST /api/calibrator/feedback), but does not explicitly exclude alternatives such as batch_calibrate or when not to use.

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