tcai_calibrate

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

With no annotations, the description carries the full burden. It discloses the main behavior: running warm-up cycles, recording |ΔF|, computing the median, and setting epsFreeEnergy. It also states the return values. It does not mention side effects beyond setting the threshold, but this is the core effect and is clearly stated.

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 three sentences, each carrying meaningful information: purpose, mechanism, and rationale. It is front-loaded and avoids redundancy or 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?

For a calibration tool with no output schema, the description provides the algorithm, the formula, the return values, and the reason for existence. It is sufficiently complete for an agent to know what will happen and what to expect.

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%, so baseline is 3. The description uses the parameter names in context (e.g., 'runs cycles warm-up cycles', 'factor× their median') but does not add new semantic information beyond what the schema already provides for each parameter.

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 action: 'Calibrate the halting threshold on the measured ΔF scale instead of a guessed constant.' This clearly states what the tool does and distinguishes it from sibling tools, which are not about threshold calibration.

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?

The phrase 'instead of a guessed constant' and the reference to the 'v2.9 critique' indicate when to use this tool: when a data-driven threshold is preferred over a fixed default. It does not explicitly name alternative tools, but the context is clear enough.

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