timps_prompt_injection_scanner

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

No annotations are provided, so the description carries the burden. It discloses that it produces a report and rewrites, which is a behavioral output. However, it does not mention whether the operation is read-only, if it modifies any existing resources, or any side effects. The word 'scan' suggests read-only but it's not explicit. It also doesn't describe limitations or prerequisites.

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, compact and front-loaded with the action verb 'Scan'. Every clause adds value, naming inputs (prompts, system messages, tool schemas) and outputs (report, rewrites). No fluff 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 tool's specialized nature and absence of output schema and annotations, the description provides enough context to understand its core function and outputs. It names the specific attack vectors and result types. However, it doesn't specify the return format or any detailed structure, which might be needed for a complex security scanner, but the key behavioral outputs are stated.

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 100% and both parameters have descriptions, so baseline is 3. The description does not add any meaning about how 'request' and 'language' relate to the scanning process. The schema descriptions themselves are vague (e.g., 'Plain-English task or context') and the tool description does not clarify that the request likely contains the prompts to scan. No added value beyond schema.

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 the tool scans prompts, system messages, and tool schemas for prompt-injection/jailbreak/data-exfiltration risks, and specifies concrete outputs ('severity-rated report and hardened prompt rewrites'). This is a specific verb+resource+output combination that distinguishes it from broader security tools like timps_security_guard or timps_ai_safety_agent.

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 implies usage for prompt-injection scanning but does not explicitly state when to prefer this tool over the many sibling security tools (timps_ai_safety_agent, timps_red_team_agent, timps_threat_intel_analyst). No clear exclusions or alternatives are mentioned, leaving the agent to infer selection.

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