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

Annotations declare readOnly, idempotent, non-destructive, and the description adds valuable behavioral context beyond that: rate limits ('Free: 30/hr, Pro: 500/hr'), privacy ('No data stored'), and the return shape ('Returns {total, by_severity, findings}'). It also notes supported languages, which are capabilities not covered by annotations.

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 front-loaded with the primary action, then systematically provides vulnerability types, supported languages, usage guidance, companion tools, rate limits, return format, and privacy guarantee. Every sentence carries distinct information without redundancy, achieving high information density in a compact form.

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 has 2 parameters and an output schema, the description covers all essential context: inputs (source code, language), capability, alternatives, rate limits, return structure, and data handling. The output schema defines the findings structure, so the description does not need to expand return values further. No significant gaps remain.

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 100%: both `code` and `language` are fully described in the input schema, including the enum values and default. The description does not add new semantic details for the parameters themselves; it only reiterates language support at a high level, so the baseline score of 3 is appropriate.

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 opens with 'Scan source code for injection vulnerabilities' which is a specific verb+resource+objective. It lists concrete vulnerability types (SQL injection, command injection, path traversal) and explicitly differentiates from sibling tools by directing secrets scanning to check_secrets, establishing a unique purpose within the companion set.

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 provides usage context ('Use to detect input-handling bugs') and explicitly names alternatives: 'for secrets use check_secrets', plus check_dependencies, check_headers, and scan_headers with their distinct purposes. This is clear when-to-use and when-not-to-use guidance, satisfying the criteria for explicit alternatives.

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