Content Quality & Drift Check

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

Annotations only indicate non-read-only status and non-destructiveness. The description adds valuable behavior context: cost ($0.03), minimum-confidence threshold (0.85), return behavior (NO_COMMIT with matched phrases), and the 'PRE-ACTION' nature. No contradictions with 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 four sentences but each one adds essential information: what it does, how it works, what it returns, and when to use it. It is front-loaded with the tool's name and cost, and contains no redundant or filler text.

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?

Given the presence of an output schema and complete parameter schema, the description covers all necessary decision-informing aspects: cost, threshold, policy specifics, output behavior, and usage context. It is fully sufficient for an agent to select and invoke the tool 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 descriptions cover all three parameters fully (100% coverage), so the description isn't required to explain them. It adds no parameter-specific semantics beyond what the schema already states, but the baseline of 3 is appropriate for complete schema coverage.

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: it runs the 'content_quality' policy and flags 12 specific types of overconfident or unverifiable phrases. It also explicitly distinguishes itself from jailbreak/safety tools, making its purpose unambiguous relative to siblings.

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 when-to-use guidance: 'before publishing agent-written copy or reports' to catch unsubstantiated claims. It also differentiates from alternatives by noting this is 'a different concern from jailbreak or safety phrasing,' effectively covering exclusions.

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