scan_prompt_injection

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

No annotations are provided, so the description must carry full weight. It lacks important behavioral details such as whether the scan is read-only, what happens on detection (e.g., blocking, alerting), or any rate limits. The behavior is underspecified for a security tool.

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?

The description is a single sentence with no redundant words. Every word is necessary and front-loaded with the action. Excellent conciseness.

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 presence of nested objects (arguments) and no output schema, the description should explain what the scan returns (e.g., boolean, list of injections, severity). It does not, leaving the agent without enough context to use the tool effectively. Annotations missing compound the issue.

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% with descriptions for all three parameters. The description adds no extra meaning beyond the schema, which is adequate. However, it does not clarify how parameters like 'arguments' structure might affect scanning or optional 'serverName' usage.

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 tool call arguments for prompt injection payloads. It uses a specific verb ('Scan') and resource ('tool call arguments'), and the purpose is well-defined. Although not explicitly distinguishing from siblings like scan_security or prompt_injection_report, the focus on arguments is unique enough.

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 when needing to check arguments for injection risks, but provides no explicit guidance on when to use this versus alternatives, prerequisites, or context. The sibling tools are varied but no exclusions or when-not scenarios are mentioned.

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