coppelia_physics_benchmark

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

With no annotations, the description carries the full burden and only partially delivers: it discloses the 2–5 scene bound, that episodes are identical across scenes, and that each scene keeps its own physics engine. It says nothing about whether simulation state is mutated or reset, how long runs take, whether scenes are paths or handles, or what a 'comparison' result looks like — critical given there is no output schema.

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 with the core action front-loaded and no filler; the trailing clause about retaining the configured physics engine earns its place by explaining the comparison's validity. Slightly cryptic phrasing ('caller-prepared', 'bounded episodes') costs it the top mark.

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 high-complexity tool with six parameters, nested objects, no annotations, and no output schema, the description is far too thin. It should at minimum explain what the four undocumented parameters do and what the caller receives back, since nothing else in the definition supplies that.

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% across six parameters including nested objects, and the description only gestures at two of them ('scenes' as caller-prepared with a configured physics engine, 'episodes' as identical and bounded). The semantics of observe, sensors, headless, and sample_every — including whether sample_every is per-episode or global — are entirely undocumented.

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 (run) and resource (identical bounded episodes across 2–5 scenes) plus the outcome (compare task outcomes), which is far more informative than a name restatement. It does not, however, differentiate itself from close siblings like coppelia_experiments or coppelia_simulate, so an agent still has to infer which one to reach for.

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 '2–5 caller-prepared scenes' and 'identical bounded episodes' implies the preconditions for use (scenes must already exist, episodes must be comparable), but there is no explicit when-to-use, when-not-to-use, or named alternative among the many simulation siblings. Usage is inferable rather than stated.

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