Program status

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

readOnlyHint and openWorldHint are already declared, so the safety bar is low and the description earns credit for adding real behavior: the exact status vocabulary (idle, running, listening, done, stopped, error), the error object shape with line number, and the hard cap of the last 50 console lines. That cap is the kind of behavioral detail annotations cannot convey.

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?

A single dense sentence, front-loaded with the resource and then the return fields. No filler and no repetition of what the title already says.

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?

There is no output schema, so the description must carry the return shape itself and does so completely: program code, enumerated status, structured error, and truncated console log. The one gap is behavior when no program has ever run, but for a zero-argument status reader this is nearly 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?

The tool takes zero parameters and the schema is empty, which is the baseline-4 case. Nothing about argument semantics is left ambiguous because there are no arguments.

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 resource (the rover program) and enumerates exactly what is returned: code, status, error, and console output. It is clear what the tool does, but it never contrasts itself with siblings like run_program, stop_program, or get_observation, so the agent must infer the boundary.

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 gives no when-to-use statement, no prerequisites, and no alternatives. The 'current/last' wording hints that it also works when nothing is running, but the agent gets no explicit signal about polling cadence or which sibling to prefer for program state versus observation data.

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