security_audit

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

With no annotations, the description carries the full burden and does so well: it declares read-only behavior, states it 'never changes sshd config or file permissions', enumerates the exact sshd directives inspected, describes the flagging rule (only world-writable or not-root-owned), and specifies the exact checks performed.

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 purpose, then behavior, return format, and capability mapping in dense but waste-free prose. Every clause contributes either scope, behavior, or output structure.

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?

No output schema exists, so the description compensates by spelling out the return JSON shape ({sshd, insecure_files:[{path, mode, owner, issue}]}). Combined with the explicit behavioral constraints, an agent has everything needed to call and interpret it.

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?

There is a single parameter (instance_id) with 100% schema description coverage, so the schema already documents the accepted formats. The description adds no parameter-level detail, which matches the baseline 3 for a high-coverage single-param tool.

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?

States a specific verb and resource ('baseline security posture of one instance') and immediately names the two signals it collects (sshd effective config and a stat of sensitive paths). An agent can differentiate it from siblings like tls_cert_check or fleet_health_snapshot without opening the schema.

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?

Clearly scopes usage to a single instance and signals the downstream use case ('powers the security-hardening detector (weak-sshd, insecure-perms)'), which tells the agent when the tool is relevant. It stops short of naming explicit alternatives or when-not-to-use conditions, so it doesn't reach a 5.

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