atlas_security

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

With no annotations, the description carries the full burden of behavioral disclosure. It describes the output behavior (findings with severity, CWE IDs, remediation suggestions) and the scope of detection, which provides helpful context. It does not mention external side effects, but 'scan' implies read-only analysis, making this a reasonably transparent description.

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 two sentences, front-loaded with the primary action ('Scan code for security vulnerabilities'), and contains no redundant or filler language. Every clause adds value—detection types, output fields, and remediation suggestions.

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 tool is fairly simple with three fully described parameters and no output schema. The description compensates by specifying the return content (severity, CWE IDs, remediation) and detection categories. It could be more complete by enumerating supported languages or performance limits, but for a static scanner, it provides sufficient operational context.

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?

The input schema already covers all three parameters with descriptions, including 'code' as the code to scan, 'context' as additional context, and 'language' as the programming language. The tool description adds no extra parameter-specific semantics beyond the schema, 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 clearly states the tool scans code for security vulnerabilities, which is a specific verb+resource. It lists concrete vulnerability types it detects (SQL injection, XSS, hardcoded secrets, weak crypto) and what it returns (severity, CWE IDs, remediation), making it distinct from sibling tools like atlas_review or atlas_bug_oracle.

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 a security scan is needed by stating 'Scan code for security vulnerabilities' and listing detection targets. However, it does not explicitly state when to use this tool over alternatives or provide exclusions, leaving the agent to infer appropriate context from the security-specific language.

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