Run shell command

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

The description goes beyond annotations by warning that the tool 'executes arbitrary code in the user's own infrastructure on their behalf' and requires explicit confirmation. It also discloses that it waits for command completion. This is critical behavioral and safety context that annotations alone do not fully express.

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 concise and front-loaded with the primary use case, followed by the behavioral guarantee and risk/confirmation warning. Every sentence adds necessary information with no 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?

For a command execution tool with four required parameters and no output schema, the description covers what it does, when to use it, that it waits, and that confirmation is mandatory. It does not describe the exact output format or timeout behavior, but the essentials for selecting and invoking the tool correctly are present.

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?

The schema already describes cmd and confirm well. The description adds context that the target is a running Lizard service's container, which gives project and service some semantic grounding. However, it does not explain how to determine or format project and service values, and half the parameters have no schema description, so the description only partially compensates.

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 runs a one-off shell command in a running Lizard service container and returns its output. It uses a specific verb and resource, and this is distinct from sibling tools like deploy_restart, logs_tail, or git_connect, so an agent can confidently distinguish it.

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 explicitly says 'Use this when the user wants to run a one-off shell command,' which gives clear invocation context. It also notes it waits for the command to finish, implying synchronous behavior, and states confirmation is required. It does not list exclusions or alternatives, but there are no closely similar sibling tools that would require an explicit when-not-to-use.

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