Submit Test Judgment

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

With no annotations, the description carries the behavioral burden. It discloses the critical non-finalizing behavior when user_approved is false, which is a key side-effect distinction. It doesn't mention whether the tool can be called multiple times, overwrite existing judgments, or require pending status, but the core behavioral trait is well covered.

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?

Two sentences, front-loaded with the primary action, and the critical caveat about user_approved is placed immediately after. No wasted words.

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 7-parameter tool with no output schema and no annotations, the description covers the essential behavior and the one parameter with complex semantics (user_approved). It doesn't describe return values or error conditions, but the core decision an agent needs—what this tool does and what finalizes—is present.

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 0%, so the description must compensate. It explains the semantic meaning of user_approved (finalization gate) and implies that score, unit_id, model_id, profile, and orchestrator_notes are the judgment components. It doesn't explain user_notes, but the schema's type info plus the description's context covers most parameters adequately.

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 action ('Record an orchestrator judgment'), the target ('one pending unit'), and the key distinction from finalization. It distinguishes itself from sibling tools like get_pending_judgments and validate_test_unit by focusing on recording a judgment rather than reading or validating.

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 implies when to use this tool: when there is a pending unit and an orchestrator judgment to record. It explains the user_approved flag's role in finalization, which guides usage. However, it doesn't explicitly name alternatives or state when not to use it, though the sibling list makes the context fairly clear.

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