Run SSH read only

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

The description explicitly claims the tool only runs read-only commands, but the 'readOnlyHint' annotation is false, creating a contradiction. Also lacks disclosure of error handling or behavior for write commands.

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 very concise (3 sentences) and front-loads the critical constraint (read-only). Every sentence adds value, though the contradiction undermines its effectiveness.

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?

Despite having an output schema, the description lacks behavioral detail (e.g., error handling, what happens if a write command is attempted) and provides no parameter context, making it incomplete for safe invocations.

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?

With 0% schema description coverage and no mention of parameters in the description, the agent gets no additional meaning for 'host' or 'command' beyond the schema.

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's purpose: running read-only commands via SSH, and the name reinforces this. It distinguishes from sibling 'run_ssh' by specifying the read-only constraint.

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 gives usage guidance: sudo is not allowed and systemctl needs --no-pager. However, it does not explicitly state when to use this tool versus alternatives, though it's implied by the read-only focus.

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