taint_analysis

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

Annotations already declare readOnly=true and destructive=false. Description adds context like framework-awareness, CWE IDs, fix suggestions, and output format. No contradictions, but minor redundancy on read-only.

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?

Front-loaded with core purpose, includes examples, comparison, and output format. Slightly dense but every sentence adds value; could be trimmed slightly.

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?

Covers sources, sinks, frameworks, output structure, CWE, suggestions, and read-only nature. Missing limitations (e.g., supported languages beyond frameworks) but sufficient for a security analysis tool.

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 clear descriptions for all 5 parameters. Description lists example sources/sinks that match enum values, adding no new semantic meaning 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 tracks untrusted data flow from sources to sinks, is framework-aware, reports unsanitized flows with CWE IDs, and distinguishes itself from sibling scan_security by focusing on data-flow vs pattern-based scanning.

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?

Explicitly states 'Use for data-flow security analysis' and directs to scan_security for pattern-based OWASP scanning, providing clear when-to-use and when-not-to-use guidance.

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