ssh_shell_send

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

The description discloses key behaviors: raw mode, dangerous command detection, and auto-adding newline. However, it omits details on what happens when dangerous commands are detected (e.g., blocked or requires confirmation), and there are no annotations to supplement. The tool could be destructive, but the description does not fully convey the safety profile.

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 two sentences, front-loaded with the core action, and every sentence provides necessary information. No redundancy or 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?

Given the absence of output schema, the description adequately states that the tool returns output. It covers the essential behavior for a send-input tool with 6 parameters, though error handling and edge cases (e.g., session timeout) are not addressed.

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%, so the schema already describes all parameters. The description adds minimal new meaning, primarily stating the default raw=false and that dangerous detection applies. This aligns with the baseline of 3 for high coverage.

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 sends input to an active shell session, specifying the raw mode and dangerous command detection. However, it does not explicitly differentiate from sibling tools like ssh_exec or ssh_exec_interactive, which could lead to confusion.

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 when an active shell session exists, but it provides no explicit guidance on when to use this tool versus alternatives (e.g., ssh_exec for single commands) or when not to use it. No exclusions or prerequisites are mentioned.

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