run_script

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

With no annotations, the description carries the full burden and delivers unusually rich disclosure: it covers restore/overwrite behavior, uploads, checkpointing, Drive flush, default shutdown, subprocess capabilities, persistence limits (workspace only, not RAM/credentials), and failure modes (Google termination, recoverable snapshots). This is exactly the side-effect and risk information an agent needs.

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?

All six sentences are information-dense and non-redundant, with the core purpose front-loaded and caveats organized logically. No filler or restatement of the schema.

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 mutation tool with no annotations and no output schema, the description covers the full execution lifecycle, persistence, default side effects, and failure recovery. It is slightly incomplete regarding return values/log retrieval and the two unnamed parameters, but it is close to complete for safe invocation.

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 0%, so the description must compensate. It implicitly documents script_path/source_directory via 'uploads the script (or... source directory)', checkpoint_seconds via 'periodically checkpoints', and stop_after via 'stops by default'. However, it never explains the 'arguments' parameter or the 'project' parameter, leaving two of six parameters semantically underspecified.

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 opening sentence names a precise action ('Run'), a specific artifact ('local Python script'), and a constrained target ('active, Drive-mounted GPU VM'). This clearly separates it from siblings like start_runtime, runtime_status, and save_workspaces, which cover VM lifecycle and workspace state rather than script execution.

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 phrase 'active... VM' establishes that the tool is for an already-running runtime rather than for starting one, and the lifecycle notes (checkpoint, flush, stop by default, long-running) give practical context. It stops short of explicitly naming sibling alternatives or stating when-not-to-use conditions, so it doesn't reach 5.

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