pt_diagnose

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

Read-only annotation is consistent, and the description adds real behavioral value by disclosing the checks performed and that deep mode reads every router's routing table. It doesn't warn about cost/latency of deep mode on large topologies, which is the main missing behavioral note.

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 the core purpose, then the enumerated checks, then the optional deep mode. Every clause adds information; nothing is 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?

There is no output schema, and the description implies findings are returned per issue but doesn't say whether results are grouped by device, counted, or how severities are represented. Given the tool's diagnostic nature, a brief note on return shape would round it out.

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 0% and the schema only says 'deep' is a boolean defaulting to false. The description fully compensates by explaining exactly what deep=true adds (routing-table reads plus unreachable-subnet listing) versus the default shallow check set.

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 ('Find misconfigurations from the live state') and enumerates the exact fault classes it detects (duplicate IPs, mixed subnets, missing gateway, cabled-but-down interfaces, powered-off devices). This clearly separates it from siblings like pt_status or pt_topology, which report state rather than diagnose faults.

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?

Usage context is clear: it operates on live state, and the deep=true mode is explicitly described as an escalation that adds routing-table reachability analysis. It doesn't explicitly name alternatives (e.g. pt_running_config for config-based checks) or state when not to use it, so it falls 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.