ps

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

With no annotations, the description carries the full burden. It discloses that the runspace is persistent and uses WinRM, but it does not explain side effects, cleanup obligations, authentication requirements, error behavior, or what happens to state across calls. Key behavioral aspects like the need to close the runspace or the output of invoke are omitted.

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, information-dense sentence. It front-loads the core purpose and then provides the operation-parameter mapping. Every phrase contributes necessary information, with no filler or redundancy.

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 tool managing persistent remote sessions, the description is incomplete. It lacks information about return values, authentication, error handling, resource cleanup if close is never called, and the format of endpoint (ep). The absence of an output schema makes this more critical, but the description does not compensate.

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 description compensates by explaining the conditional parameter requirements: 'open needs ep=; invoke/close need id=; invoke uses script='. This adds meaning beyond the raw schema by mapping parameters to operations, though it does not define each parameter's full purpose or format.

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 clearly states the tool manages a 'Persistent PowerShell runspace (WinRM)' and enumerates the operations (open/invoke/close), which gives a specific verb-resource mapping. It is distinct from siblings by naming the resource, but it does not explicitly differentiate itself from sibling tools like 'exec' or 'endpoint'.

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 implies usage through the term 'Persistent' and lists operation-specific parameter requirements, which gives some context on when to use each operation. However, it does not explicitly state when this tool should be preferred over siblings or mention exclusions/alternatives.

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