pt_cli

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

Without meaningful annotations, the description carries the burden and does well: it discloses that config mode reports only failing lines (successes are silent), that sub-modes work and 'end' is auto-appended, that exec returns output, and that save=true appends 'write memory'. It omits whether config changes persist to startup-config without save, and what happens if the device is off or unnamed.

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?

Three tight sentences; the core action is front-loaded and each clause adds operational detail (mode behavior, return semantics, save side-effect) with no 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?

No output schema and no annotations beyond openWorldHint, so the description has to cover everything. It handles mode semantics and the save side-effect but leaves the device identifier format and failure/error behavior underspecified for a 4-parameter command-execution tool.

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 description coverage is 0%, so the description must compensate. It explains mode values, save's effect, and implies commands are individual lines, but the `device` parameter is never defined (name? ID? from pt_topology/pt_device?), and it doesn't resolve the string-vs-array ambiguity for `commands`.

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 ('Run IOS commands on a router/switch/ASA') and distinguishes the two modes. It also points to pt_show as the preferred tool for EXEC output, which separates it from at least one sibling. It doesn't clarify its boundary against higher-level siblings like pt_apply_feature or pt_configure_hosts.

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?

Gives explicit per-mode guidance: mode=config enters lines from global config with 'end' appended, mode=exec returns output and should be avoided in favor of pt_show. That covers when to use each mode and names one alternative. No guidance on when to prefer this over the feature-specific siblings.

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