diagnostics

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

No annotations are provided, so the description carries the behavioral disclosure burden. It explicitly declares 'Read-only views', which is the key safety trait. However, it does not surface nuances such as packet_capture's start/stop/fetch lifecycle or ping's active network probes, which a fully transparent description for a 9-action tool would mention.

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?

Two sentences, front-loaded with a concrete scope list and followed by a single high-value self-help instruction. No filler or redundant elaboration.

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 31-parameter, 9-action tool with no output schema and no annotations, this description is deliberately broad and routes the agent to action='help' for per-action details. The schema's per-parameter action tags compensate for missing prose, but return semantics and per-action behavioral differences are not covered in the tool description itself.

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 coverage is 100% and every parameter already has an action-tagged description, so the schema does the heavy lifting. The description only adds a meta-instruction to call action='help' for per-action fields and rules, which is useful but does not explain individual parameters. Baseline 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 states a specific purpose: read-only views of the firewall's current state, listing six concrete domains (neighbours, interfaces, state table, logs, captures, reachability). This makes the tool's scope clear and distinguishes it from config-oriented siblings by the 'read-only' framing, though it does not explicitly name an alternative.

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 'Read-only views' qualifier gives clear context: use this for inspecting current firewall state rather than modifying configuration. The explicit instruction to call action='help' for each action's fields and rules is actionable entry-point guidance. It does not state exclusions or name sibling tools, so it stops short of a 5.

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