deep_scan

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

With no annotations, the description carries full burden. It discloses the use of LLM (Claude Haiku 4.5 default), model options with cost implications, required environment variables, and truncation behavior. It lacks details on expected output structure but covers key operational traits.

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 brief (three sentences) but packed with essential information. It front-loads the purpose and then efficiently adds behavioral details, model options, and prerequisites. Every sentence adds value with no redundancy.

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 complexity (8 parameters, enums, defaults, no output schema), the description covers the main aspects: purpose, model choice, cost, env vars, and truncation. It does not describe the return value structure, but since no output schema is provided, the parameter 'format' gives some indication. Slightly more detail on expected output would improve completeness.

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?

All 8 parameters are described in the schema (100% coverage). The description adds value by providing context beyond the schema, such as the example of passing 'model: sonnet' and explaining that 'maxBytes caps cost' and 'focus narrows the prompt'. This additional guidance enhances parameter understanding.

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 specifies a clear verb-resource combination: 'LLM-powered deep security analysis' for vulnerabilities that pattern-matching cannot detect. It enumerates specific vulnerability types (IDOR, business logic flaws, etc.), distinguishing it from sibling tools that likely rely on pattern matching.

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 explains when to use this tool (for vulnerabilities undetectable by pattern matching) and mentions default model and required API keys. However, it does not explicitly state when not to use it or compare with sibling tools for alternative use cases.

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