security_audit

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

With no annotations, the description fully discloses behavior: it is read-only, checks sshd effective config (listing specific directives) and sensitive paths (listing criteria for world-writable or not root-owned), and never modifies anything. Return format is given. No contradictions.

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 four sentences long, each serving a distinct purpose: overall intent, details of checks, assurance of non-modification, and output format. It is front-loaded and contains no redundant words.

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 the tool's purpose, inputs, exact outputs, and behavior. It does not mention error cases or performance, but for a straightforward audit tool, it is sufficiently complete.

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 only parameter, instance_id, is described in the schema as 'Instance ID or name.' The description does not add additional detail beyond what the schema provides, so baseline 3 applies due to 100% schema coverage.

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 states the tool performs a 'baseline security posture' audit on one instance, specifying it checks sshd config and sensitive file permissions. This clearly distinguishes it from sibling tools like get_logs or run_command.

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 explicitly says it is read-only and never changes configuration, giving context for when to use it safely. It also mentions it powers a security-hardening detector, implying use cases. However, it does not explicitly contrast with alternatives like check_status or specific security tools.

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