QA Judge (paid, credits or x402)

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds substantial context beyond these: cost ($0.10 USDC), latency (~1s to ~30s), deterministic grading behavior, the literal interpretation of the rubric, score bands, and output details (signed attestation). This enriches the agent's understanding of side effects, resource usage, and response characteristics without contradicting any annotation.

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 organized with clear labeled sections (WHAT, WHEN, WHEN NOT, COST, LATENCY, OUTPUT, Bands), making it easy to scan and parse. Every sentence serves a distinct purpose—purpose, usage guidance, exclusions, cost, latency, output format, and thresholds—with no fluff or redundant restatement of schema/annotations.

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 3 parameters, an output schema, and rich annotations, the description covers all critical operational aspects: exact use cases, alternatives, cost, latency, determinism, score bands, and output structure. The presence of an output schema means return values need not be exhaustively documented, but the description still summarizes the key output fields and thresholds, leaving no significant gaps.

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 the baseline is 3. The description adds meaningful context by explaining that the judge is 'literal and grades exactly what you write,' which directly informs how the rubric parameter should be constructed, and ties the weight parameter to the returned per-criterion weighted score. This goes slightly beyond the schema's structural descriptions.

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 'WHAT: grades an agent output against your rubric and returns a 0-100 weighted score with per-criterion evidence and a signed attestation,' which is a specific verb+resource statement that immediately clarifies the tool's function. It further distinguishes itself from the sibling tool oracle_verify_work by explicitly naming the alternative for citation truth-checking.

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 includes explicit 'WHEN' and 'WHEN NOT' sections, listing concrete use cases (accepting/rejecting deliverables, ranking candidate answers, logging QA receipts) and exclusions (subjective taste, citation truth-checking alone, vague rubric). It also names the specific alternative tool, oracle_verify_work, for one of the exclusions, providing clear decision guidance.

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