strip_prompt_injection

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

With no annotations, the description carries the burden, and it does well by enumerating exactly what it neutralizes and adding an explicit cost note ('0.02 USDC on Base L2'). It does not state the shape of the returned sanitized text or failure behavior, a minor gap for an otherwise clear transformation tool.

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?

A single front-loaded sentence with zero filler; every clause carries content, and the parenthetical pricing is compact and useful for selection. It is appropriately sized for an agent to parse quickly.

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 low-complexity sanitization tool with fully described parameters, the description covers the core behavior and cost. It slightly under-specifies the return value and whether paymentSignature is mandatory in practice, but an agent has enough to select and invoke it.

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 structured fields already document both parameters. The description adds no meaning about how payload should be shaped or how paymentSignature relates to the 0.02 USDC fee beyond what the schema already states, warranting the baseline score.

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?

States a precise verb ('Neutralizes') and a well-defined resource: indirect prompt injections, system prompt leak probes, jailbreak tokens, and hidden instruction tags in untrusted text. The action clearly marks it as a sanitizer rather than a detector, distinguishing it from the sibling prompt_injection_jailbreak_classifier.

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 intended use is implied by 'in untrusted text': an agent can infer this is the tool to strip adversarial LLM instructions before further processing. But the description never names the classifier sibling or states when not to use it, leaving routing partially to inference.

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