Screen for Prompt Injection

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

Annotations declare readOnlyHint=true and destructiveHint=false, so the description doesn't need to restate safety. It adds value by disclosing the cost ($0.03 USDC on Base) and the payment mechanism, which is a significant behavioral trait. The description also mentions detection categories (10) giving functional scope beyond 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?

Two sentences with zero waste. States purpose, scope, and cost efficiently. Front-loaded with the core function first.

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?

Has output schema and 100% schema coverage, so the description doesn't need to explain return values or params. For a single-purpose screening tool with readOnly annotations, the description plus schema fully covers what an agent needs to invoke it correctly, including the payment requirement.

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 schema documents all 5 parameters well. The description adds minimal param-specific detail (char limit mentioned in schema, sensitivity enum in schema). Baseline 3 is appropriate since the schema does the heavy lifting and description doesn't need to compensate.

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 uses a specific verb+resource ('Screen text for prompt injection and jailbreak attacks') and clearly states the core function before passing to an LLM. It distinguishes itself from sibling tools (qr, image, dns, etc.) by its unique security domain. Adding the 10 attack categories and cost provides concrete scope.

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 clearly states WHEN to use it ('before passing it to an LLM') which is explicit usage context. It doesn't name alternatives or exclusions, but the domain is distinct enough from siblings that alternatives aren't obviously relevant. The payment flow is described in the schema parameter._payment.

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