remote_session_open

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

Annotations already declare destructiveHint=true, openWorldHint=true and non-idempotent, so the safety profile is covered; the description adds genuinely new behavior — session lifetime ends only on close or server process exit, SSH shell state (cwd, exported variables) persists, and WinRM reuses a single PSRP runspace. What is still missing is what happens on a name collision and whether connection/credentials are required at open time.

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 short sentences, front-loaded with the action and followed by the persistence semantics that actually matter for deciding to call it. No filler, though the trailing sentence about WinRM is terse enough that it reads slightly as an implementation note rather than agent-facing guidance.

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?

An output schema exists, so return values need not be explained, and the annotation set covers the risk profile, leaving the description to carry lifetime and state-persistence semantics — which it does. The remaining gap is parameter-level (profile and connection), which materially affects correct invocation of a session-opening 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 carries the full burden, yet it only indirectly explains two of four parameters — 'named' maps to name and 'SSH shell or WinRM' maps to shell. The profile and connection parameters, including the connection object that presumably carries host and credentials, get no explanation at all, leaving the most consequential input undocumented.

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 opens with a specific verb and resource — 'Open a named persistent SSH shell or WinRM PowerShell runspace' — which tells an agent exactly what is created and the two transport modes supported. It does not explicitly name a sibling like remote_session_execute or remote_session_close to sharpen the boundary, so it falls short of a 5.

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 is only implied: the word 'persistent' and the note that cwd/exported variables persist tell an agent this is for stateful, multi-step work rather than one-shot commands. There is no explicit 'use this instead of remote_execute when…' statement, and no mention of when a persistent session is unnecessary or what to do if one already exists.

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