sim_screenshot

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

With no annotations, the description carries the full burden. It usefully discloses the gui=True prerequisite, which is a genuine behavioral constraint. But it omits return characteristics (image format, size, viewport vs full scene), latency/cost, and failure behavior when gui is disabled.

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 short sentences, zero filler, with the action stated first and the prerequisite immediately after. Every clause earns its place.

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 simple zero-parameter tool this is nearly complete — purpose plus the one gating precondition. The only gap is the absence of any indication of what the returned image looks like (format/dimensions), which matters since there is no output schema.

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, so there is nothing for the description to clarify; baseline for a parameterless tool is 4. The empty schema is self-consistent with the description implying a no-argument capture.

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+resource: 'Capture the viewport as an image.' An agent immediately understands it returns a rendered screenshot of the simulation viewport, which is clearly distinct from siblings like sim_set_camera or sim_get_stats. It stops short of explicitly contrasting itself with any sibling, so 4 rather than 5.

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 a real precondition — the daemon must be started with gui=True — which tells the agent when this tool will actually work. However, it offers no guidance on when to prefer this over alternatives (e.g. sim_set_camera + capture workflow) or what to do if the daemon wasn't started with gui=True.

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