Screen untrusted text for prompt injection

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

Beyond the annotations (readOnly, idempotent, non-destructive), the description reveals what the tool actually does: asks fixed yes/no signals, counts invisible Unicode characters, returns a three-way verdict with probabilities, and clarifies that a clean verdict only lowers risk rather than proving safety. This is substantial behavioral context.

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 concise sentences front-load the main action, then describe the signals, output, and a key limitation. Every sentence contributes meaningful information and there is no filler or repetition.

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 output schema exists and annotations cover safety/idempotence, the description provides what an agent needs: input types, screening mechanism, verdict values, and a caution about interpreting a clean result. No critical behavioral gap remains.

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 already documents path, text, no_at_or_below, and yes_at_or_below thoroughly. The description adds context about the screening behavior but does not add any parameter-specific meaning, so the baseline 3 applies.

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 ('Check') and names concrete targets ('web page, issue, email, or file') and a clear goal ('for prompt injection'), and it states the timing ('BEFORE reading it into your context'). It does not explicitly distinguish this tool from its siblings such as jev_check or jev_triage, so it stops short of a 5.

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 gives clear when-to-use guidance: apply it to content you did not write and before pulling it into context. It does not mention when not to use it or name alternative tools, so there are no explicit exclusions or sibling trade-offs.

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