prompt_injection_scanner__scan_text

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

With no annotations, the description carries the full burden. It largely rises to that by disclosing the concrete detection classes (instruction-override, spoofed chat-template roles, hidden/invisible text, AI-directed content, exfiltration), which is real behavioral substance. It does not disclose what a scan returns, whether findings are blocking, whether it is heuristic/read-only, or any permission needs, and there is no output schema to fill that gap.

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 the verb first and no filler; the em-dash list of input types earns its place by narrowing scope. The parenthetical detection list is long but informative rather than redundant, so it is dense but not padded.

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 two-parameter scanner with no annotations and no output schema, the definition covers purpose and detection scope adequately but omits the return shape and any safety/heuristic caveats. Those gaps are tolerable but leave the agent guessing about results.

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 both parameters are already documented and the baseline is 3. The description adds some value by characterizing what 'content' typically holds (RAG chunk, web page, document, tool result), but says nothing about the optional 'label' parameter or any format constraints.

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?

Specific verb (scan) plus resource (a text string), with the input types enumerated (RAG chunk, scraped page, document, tool result) and the detection taxonomy spelled out, which meaningfully separates it from memory_poisoning/tool_poisoning scanners. It stops short of naming its own siblings (scan_file, scan_directory) or stating that file inputs belong elsewhere, so the routing is inferable rather than explicit.

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 phrase 'before it reaches a model's context' implies the intended pre-ingestion use case, which is genuine usage context. However there is no explicit when-to-use/when-not, no prerequisites, and no routing to alternatives such as scan_file or scan_directory for non-string inputs.

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