SSH MCP Server

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It partially compensates by disclosing the return structure (stdout, stderr, exit code) in lieu of an output schema. However, it omits critical behavioral traits: that execution is destructive/mutative, requires network connectivity, or handles authentication failures.

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 efficiently structured: first defines the operation, second describes the return value. No redundant phrases or unnecessary verbiage. Every sentence earns its place.

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 high-risk remote execution tool with 7 parameters and no annotations/output schema, the description is minimally adequate. It covers the return structure but misses security implications (arbitrary code execution), error handling behaviors, and side-effect warnings that would be expected for this complexity level.

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 100%, establishing a baseline of 3. The description adds no parameter-specific guidance beyond the schema (e.g., no syntax examples for privateKeyPath, no guidance on timeout units beyond the schema's 'milliseconds').

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 specific verb 'Execute' and resource 'command on a remote host via SSH'. While it implicitly distinguishes from file-centric siblings (ssh_download, ssh_upload, etc.) by specifying 'command execution' versus file operations, it lacks explicit differentiation from ssh_diagnose.

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 provides no guidance on when to use this tool versus alternatives like ssh_diagnose for troubleshooting. It also lacks prerequisites such as authentication requirements (despite auth parameters existing) or security warnings about executing arbitrary commands.

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