router_security_audit

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

The description explicitly says 'read-only audit,' which aligns with the annotations readOnlyHint=true, idempotentHint=true, and destructiveHint=false. However, it adds little behavioral context beyond what the annotations already provide; it does not disclose output format, permissions, or what happens when issues are found. This is acceptable given the strong annotation coverage, but not exceptional.

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 a single, front-loaded sentence that immediately identifies the operation ('read-only audit') and then lists the specific checks. Every word earns its place, with no redundancy or filler.

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?

For a no-input, read-only audit tool, the description is largely complete: it names the audit areas and is backed by clear annotations. The absence of an output schema means the description might ideally mention what the returned result looks like, but the verb 'audit' strongly implies a report of findings, so this is a minor gap.

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 tool has zero parameters, so there is nothing for the description to explain about inputs. The schema coverage is effectively 100% and the description correctly implies that invoking this tool requires no arguments. A baseline of 4 is appropriate for a no-parameter 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?

The description states a specific verb ('Run'), a clear resource ('router security audit'), and enumerates the concrete audit categories: unsafe WAN input, management port forwards, HTTP-only LuCI, and SSH password authentication. This clearly distinguishes it from sibling tools like router_firewall_status or router_luci_pages, which are more general or unrelated.

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 makes the intended use case clear: perform a read-only security audit of specific router security concerns. It does not explicitly name alternatives or exclusion conditions, but the audit scope and read-only nature give an agent enough context to select it over real-time stats, logs, or configuration tools.

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