Execute command in guest (QEMU agent)

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

Description adds value beyond annotations by explaining the asynchronous nature (returns pid, poll for output). Annotations already indicate not read-only, not inherently destructive, and not idempotent. No contradiction. Could mention that command may have side effects based on execution, but overall transparent.

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?

Two sentences, no fluff. Front-loaded with the primary purpose, then secondary information (return and next step). Every word contributes meaning.

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?

Considering the lack of output schema, the description effectively communicates the input parameters and the process flow (run command, get pid, poll for output). It could mention potential errors, timeouts, or resource implications, but for a tool with 4 params and annotations, it is adequately complete.

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% (only command and input_data have descriptions). The description does not detail node or vmid parameters, relying on their common understanding from sibling tools. It adds marginal value by stating the functionality but doesn't compensate for missing schema descriptions on half the parameters.

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 it runs a shell command inside a VM via QEMU guest agent, identifies the return value (pid) and next step (poll exec_status for output). It distinguishes the tool from other VM agent tools like vm_agent_get_hostname or vm_agent_set_user_password.

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 implies that exec_status should be polled to get output, providing a clear usage pattern. It doesn't explicitly state when to use this vs alternatives, but given the sibling list with specific agent tools, the context is sufficient. Could benefit from mentioning 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.