Judge one agent turn

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

Given no annotations, the description discloses core behavior: it returns a decision and gate action, explicitly states what it measures and what it ignores, and provides imperative next steps. It does not discuss auth or rate limits, but these are not suggested by context; the behavioral disclosures are substantial.

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 well-structured: a clear opening statement, a purpose clarification, and a compact mapping of gate actions. Every sentence adds value, and the arrow-format list is easy to parse.

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 tool with four parameters, an output schema, and no siblings, the description covers the essential decision logic, expected usage sequence, and gate handling. The output schema covers return values, and the description fills behavioral gaps. It is complete for an agent to use correctly.

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 75%, so most parameters are described in the schema. The description adds context about inputs/outputs implicitly (e.g., 'regenerate' implies output is a draft) but does not elaborate on parameter-specific semantics. Baseline of 3 is appropriate.

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 identifies the tool's function with a specific verb ('Judge') and resource ('one agent turn'), and adds distinguishing context: it measures 'process shape, not whether the goal was reached.' This differentiates it from any generic evaluation tool and sets precise expectations.

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 provides explicit action guidance for each gate result (release -> show, clarify -> regenerate then call again, suppress -> stop or escalate, none -> observe only). It also states when to act ('before showing the reply'). It lacks explicit when-not-to-use alternatives, but no siblings exist and the context is clear.

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