remote_exec

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

Annotations already indicate idempotent and non-destructive. Description adds that execution is restricted to named recipes and pre-configured hosts, which is useful beyond annotations. No contradiction found.

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 with parenthetical clarification, no filler. Front-loads the core purpose and constraints efficiently.

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?

Covers core purpose, constraints, and preconditions adequately. Lacks details on output format or error behavior, but given no output schema and 6 parameters, the description is sufficiently complete for an agent to use the tool correctly.

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 has 100% parameter descriptions, so baseline is 3. Description does not add parameter-level detail but reinforces the overall constraints (e.g., 'remote argv must be on the host allowlist') which indirectly relates to the params parameter.

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?

Description clearly states the action ('Run'), the resource ('named recipe on a configured SSH host'), and explicitly excludes free-form shell, distinguishing it from potential siblings like remote_list or agent_execute_todo.

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 explicit context: only named recipes, no free-form shell, prerequisites (host and recipe must exist, argv allowlisted). Does not name alternative tools but effectively tells when not to use this tool.

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