sim_up

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

With no annotations, the description carries the full burden and does well: idempotency, a blocking wait, a host prerequisite (xhost +local:docker), and a significant latency warning on first start (Nucleus asset download and shader cache builds take minutes). Missing only what happens on failure/timeout.

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?

Front-loaded purpose sentence, then a compact per-parameter block with zero filler. Slightly terse formatting, but every line adds information an agent needs.

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?

Output schema exists so return values need not be described. The description covers prerequisites, latency, idempotency, and most parameter semantics for a 6-param tool, leaving only the timeout parameter's meaning unaddressed.

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 0%, so the description must compensate and largely does: it explains robot (repo-relative path with example), usd (overrides config), gui (screenshot dependency), ground (floor removal for range tests), and extra_args (passed verbatim to scripts/simd.py with example). Only timeout is left unexplained.

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?

States a specific verb and resource ('Start the daemon container and wait until it answers'), plus a scoping trait ('Idempotent'). Combined with the sim_* sibling family, an agent can distinguish this from sim_down/sim_reload without opening a schema.

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 conditional guidance tied to other tools: gui=True is required for sim_screenshot, and ground=False is for range tests. It doesn't explicitly name sim_down as the inverse or state when NOT to call it (e.g. already running), but the operational context is clear.

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