prompt_injection_scanner__scan_text

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

No annotations are provided, so the description carries the full burden. It usefully discloses what detection signal categories are covered and implies a read-only inspection, but says nothing about return shape (severity, offsets, pattern IDs), latency, or whether it inspects the content only versus any embedded markup.

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 that leads with the action and resource before the parenthetical detail list. No filler, though the long parenthetical of detection categories makes it dense.

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?

With no annotations and no output schema, the description is the only source of behavioral information. It covers what is scanned and why, but leaves the agent guessing about the findings structure and whether a clean result is signalled distinctly from a hit.

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% and both parameters ('content', 'label') are described in the schema itself. The description adds nothing about parameter meaning, which is acceptable at full coverage but earns only the baseline.

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 specific verb ('scan') and resource ('a text string') and then enumerates the exact payload classes it targets (instruction-override, spoofed chat roles, hidden text, exfiltration), which cleanly separates it from the many other *_scan_text siblings. It stops short of naming a sibling or stating an explicit boundary, so it is clear but not fully differentiated.

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' gives a usable trigger point, and the input examples (RAG chunk, scraped page, document, tool result) hint at the intended call sites. However, no alternatives are named despite siblings like secret_scanner__scan_text, a2a_auditor__scan_text, and prompt_injection_scanner__scan_file existing, and no when-not-to-use condition is given.

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