detect_prompt_injection

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

With no annotations provided, the description must carry the behavioral burden. It mentions 'context-aware risk scoring' and lists detected patterns, but does not disclose what happens after detection (e.g., returns a boolean, score, or flagged text). No side effects or safety info is given.

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?

Two sentences, no wasted words. First sentence states the core purpose, second adds meaningful detail. Well front-loaded.

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?

Input parameters are well covered, but no output schema exists and the description omits any mention of return values or structure. For a detection tool, understanding the output format is important for correct usage.

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?

The schema covers 100% of parameters with descriptions. The description adds 'context-aware risk scoring' and lists specific injection types, providing meaning beyond the raw parameter definitions, especially for the 'context' enum values.

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 clearly states 'Analyze text for prompt injection attempts' and lists specific attack types (instruction overrides, identity manipulation, etc.), which is a specific verb+resource. Among sibling security tools, it uniquely targets prompt injection, so it distinguishes well.

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 does not explicitly state when to use this tool versus alternatives like scan_secrets or detect_tool_poisoning. It implies usage for analyzing text for injection, but provides no exclusion criteria or context-based guidance.

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