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

Annotations already indicate destructiveHint=true and readOnlyHint=false, so the description's addition of 'persistent' and 'wait for it to finish' adds behavioral context about state persistence and synchronous execution. It also discloses the return format (exit code, stdout, stderr). While it doesn't describe permission levels or side effects beyond the command's own effects, the annotation covers destructiveness. No contradiction with annotations.

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 two sentences, front-loaded with the main action. Every sentence provides necessary information: what the tool does, what it returns, and a crucial prerequisite. There is no redundancy or filler, making it highly concise and well-structured.

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 complex tool with 6 parameters and no output schema, the description covers the essential behavioral contract: execution, waiting, and return values. It omits details about the exact return structure (e.g., JSON fields) and failure modes like timeouts, but the timeout parameter is documented in the schema. It is adequate for an agent to select and invoke the tool correctly, though not exhaustive.

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 description coverage is 100%, with each parameter (id, command, cwd, env, args, timeout_ms) having a clear description. The tool description does not add extra meaning beyond the schema, and only reinforces that the machine must be running. Given the schema already fully documents the parameters, a baseline score of 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 uses a specific verb ('Run'), identifies the resource ('a persistent Linux machine'), and states the core behavior ('wait for it to finish'). It also lists the return values (exit code, stdout, stderr), which distinguishes it from sibling tools like scalix_computer_read_file or scalix_computer_write_file. The purpose is unambiguous and differentiates from machine lifecycle tools.

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 clear context: it runs commands on a persistent Linux machine, waits for completion, and returns output. The critical prerequisite 'The machine must be running' implicitly tells the agent to check scalix_computer_list or start the machine first. However, it does not explicitly mention alternatives or when not to use it, hence not a 5.

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