remote_exec

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

With no annotations, the description fully covers behavioral traits: HTTPS transport, auth token requirement, default-deny allowlist, and that token values are never returned. This is comprehensive for a secure execution tool.

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 one paragraph of 5 sentences, efficiently conveying all necessary information without redundancy. Could be slightly more structured, but it is not verbose.

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?

The description does not mention the return value or output format (e.g., stdout, exit code). With no output schema, this is a significant gap. It also does not describe timeout behavior beyond mentioning the parameter. Thus incomplete for an execution 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 coverage is 100%, so descriptions per parameter are adequate. The description adds context that host is a host_id from remote_hosts and command must be allowlisted, but does not go beyond schema details for stdin and timeout. Baseline 3 is appropriate.

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 executes a shell command on a remote host over HTTPS, with specific resource and action. It implicitly distinguishes from sibling tools which are memory or topic related.

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 explicit conditions: requires a remote_hosts entry in partner_tools, otherwise invalid_request error; and commands must be allowlisted, otherwise forbidden error. This guides the agent on prerequisites and failure modes.

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