PQS - Prompt Quality Score

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

Strong disclosure for a paid operation with no annotations: explicitly states cost ($0.50 USDC), payment mechanism (x402), judging methodology, and return structure. Would benefit from mentioning if the charge is immediate/reversible or if the operation is idempotent, but covers critical financial and methodological traits well.

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?

Three sentences with zero waste: sentence 1 defines the comparison methodology, sentence 2 specifies outputs, sentence 3 discloses cost. Information is front-loaded and logically ordered. Excellent density without verbosity.

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?

Comprehensive for a 3-parameter tool with no output schema: description covers return values (winner, scores, recommendation) that would otherwise be unknown, and discloses financial requirements. Minor gap regarding error handling or async status, but adequate for safe invocation.

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 coverage is 100%, so baseline applies. The description mentions 'prompt' in context but does not elaborate on parameter semantics beyond what the schema already documents (prompt content, vertical enum values, API key source). No additional parameter guidance provided in description prose.

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?

Excellent clarity: specifies exact action ('Compare'), specific models ('Claude vs GPT-4o'), methodology ('PQS', 'third model judge'), and output types. Clearly distinguishes from siblings optimize_prompt (single model optimization) and score_prompt (single model scoring) by emphasizing the head-to-head nature.

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?

Implicitly guides usage through return value description ('winner', 'recommendation on which model to use'), indicating this is for decision-making between models. Lacks explicit 'when not to use' or direct comparison to siblings, but context is clear enough to infer appropriate use cases.

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