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

With no annotations, the description carries the full burden of explaining behavior, and it does so well: cost of €0.003 per request, billing to the API key in the Authorization Bearer header, the exact condition that triggers the model call, 6-language coverage, and the list of detection categories. It also sets a calibration expectation ('Risk assessment, not a guarantee').

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?

It is dense but front-loaded: the purpose and limits come first, then the detection categories, then the cost and model-call rule, then the parameters. Every sentence adds new information, and nothing is filler.

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?

An output schema exists, so the description need not explain return values. It still covers cost, authentication, the trigger for the expensive path, and the scope of detection, which is more than enough for a two-parameter tool.

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 0%, so the description has to compensate, and it does: text is explained with concrete sources, and deep is explained as 'always ask the model too'. One flaw is that the description calls deep a 'bool', while the schema types it as a string; that mismatch weakens the semantics.

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 names a specific verb and resource: it screens text for jailbreak phrases, hidden text, base64-encoded instructions (2 levels deep), markdown-image URL exfiltration and API-key-shaped secrets. That is far more specific than a generic 'detect' tool, but it never names a sibling (profanity_filter, url_safety, image_moderate) to distinguish this tool from them.

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?

It gives a clear usage context: screen user input, a document, or a tool result. It also explains when the expensive path runs: only when the regex score is ambiguous (0.3-0.7) or deep=true. It gives no explicit when-not-to-use guidance or alternatives.

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