SSH MCP Server

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

With no annotations provided, the description carries full burden but omits critical behavioral details: it does not disclose the read-only/safe nature of the operation, the output format/structure (crucial for a listing tool without output schema), connection timeouts, or authentication failure behaviors. Only mentions SFTP protocol.

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?

Single sentence, front-loaded with action verb, zero redundancy. Efficiently conveys core purpose without extraneous text.

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?

Adequate for a listing tool but has clear gaps: missing output specification (file names only? metadata? recursive?), no mention of pagination for large directories, and no safety/permission context given the lack of annotations and output schema.

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 100% with clear descriptions for all 6 parameters (host, port, username, etc.). The description adds no additional parameter semantics, meeting the baseline for high-coverage schemas.

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?

Excellent specificity: 'List files' is a precise verb phrase, 'directory on remote host' identifies the resource, and 'via SFTP' distinguishes the transport method from siblings like ssh_exec (which uses SSH) and ssh_read_file (which reads file content).

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?

Provides implied usage through clear naming (list vs download/read/write), but lacks explicit guidance on when to prefer this over ssh_exec (which could also run `ls`) or how it relates to ssh_diagnose. No 'when-not' or alternative recommendations stated.

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