scan_for_prompt_injection

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

No annotations are present, so the description carries the full burden. It discloses that the tool uses SonnyLabs.ai API and requires a Bearer token, indicating an external network call. It also describes the return type (a dictionary). However, it does not mention rate limits, data sent to a third party, error handling, or other side effects. This is moderately transparent but not richly detailed.

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 well-structured with a clear opening, context, an Args block, and a Returns line. It is not overly long, though one sentence ('Detects attempts to manipulate AI behavior through prompt injection') is somewhat redundant with the first line. Overall efficient and 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?

The description covers all parameters and the return type, and it provides compliance context. An output schema exists, so the return format does not need full explanation. However, it lacks details on potential errors, rate limits, or the behavior of the external API. For a tool with external side effects, this is a small gap but not critical.

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 0%, but the description compensates excellently by explaining each parameter: user_input is the text to scan, sonnylabs_api_token is a Bearer token, sonnylabs_analysis_id is the analysis ID, and tag is an optional identifier with a default. This adds meaningful context beyond the raw 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 it 'Scans user input for prompt injection attacks using SonnyLabs.ai API', providing a specific verb, resource, and scope. It distinguishes itself from siblings by focusing on prompt injection detection, while other tools handle different AI Act compliance aspects.

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 gives clear context: scanning user input for prompt injection and helping with EU AI Act Article 15 cybersecurity requirements. It implies when to use it (whenever prompt injection scanning is needed), but it does not explicitly mention alternatives or exclusions. Still, the context is strong enough for an agent to select this tool over siblings.

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