calibrate_judge

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is known. The description adds value by explaining the output semantics (agreement and directional error trend) and clarifies that over-crediting indicates the length/self-preference failure mode, which is non-obvious behavior not in annotations.

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 two sentences, immediately states the main purpose, and avoids redundancy with schema/annotations. Every clause earns its place.

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?

The description covers what the tool does, what inputs to provide, and what output to expect (agreement and bias direction). Combined with a complete schema and output schema, the agent has enough to select and invoke correctly. No critical gaps are evident.

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?

All three parameters have thorough schema descriptions, so the schema carries the semantic load. The description adds only a brief restatement that the booleans are aligned, but it does not provide new parameter-level detail beyond the schema's 'aligned 1:1' note.

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 function with a specific verb ('Check an LLM judge against ground truth') and identifies the required inputs (aligned booleans). It distinguishes from siblings by focusing on calibration against ground truth and explaining the over-crediting failure mode, which is unique among the sibling list.

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 description gives clear context: use this when you have a labelled slice and want to compare judge verdicts to ground truth. However, it does not explicitly mention when not to use it or name alternative tools such as verify_judge_bias, so it falls short of a 5.

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