Run a command in a lab

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

Annotations declare readOnlyHint=false and destructiveHint=false but leave the agent with no sense of consequence; the description supplies that by warning the command "can change the lab" and requiring user confirmation for non-read commands. It also discloses the return shape (exit code and output). It does not cover timeout behavior, permissions, or side-effect scope, so it stops short of a 5.

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?

Three short sentences with no filler: what it does and returns, how to pass the command, and the caution. The caution and the critical usage rule are front-loaded rather than buried.

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?

An output schema exists, so return-value detail is optional, yet the description still summarizes it; the mutation warning and command format cover the main risks of an exec tool. The only real omissions are timeoutSeconds semantics and any note on environment/working-directory context or failure modes.

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 50%: lab and service are documented in-schema, while command and timeoutSeconds are not. The description compensates well for command by specifying it is an argv list and showing the shell-line form, but says nothing about timeoutSeconds, leaving one of four parameters undocumented everywhere.

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?

Names a specific verb and resource ("Run a command") and scopes it precisely to "one of a running lab's services," which separates it from the container-level siblings exec_in_container and compose_exec. It does not name those siblings explicitly, but the lab-scoped framing is enough for an agent to route correctly.

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?

Gives concrete invocation guidance (command is a list; use ["sh", "-c", "…"] for a shell line) and a clear conditional rule for the risky case: confirm with the person first unless the command only reads. No exclusions or explicit alternative tool are named, but the when-to-be-careful guidance is unusually actionable.

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