roll_dice

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: it discloses that this is a physics simulation, that it blocks until all dice come to rest, that dice bounce and can hit other objects, and that tilt/cocked disputes are possible. It doesn't cover failure modes (e.g. a die that never settles) or what happens to objects knocked over, which keeps it off a 5.

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 with the mechanism, then the return contract, then the bounce caution — each sentence earns its place. Markdown mangling ('all\nhave come to rest') and the slightly run-on return sentence cost a point.

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?

Compensates well for having no annotations and no output schema by describing the return payload (value, tilt, total, `cocked`) inline. The one material omission is the identity of `guids`, which leaves an agent guessing on the required argument.

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 explains `cocked_tilt` well (degrees, default 10, 'for flat surfaces') but says nothing about `guids`, the sole required parameter — an agent must guess these are the die/coin object GUIDs.

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 plus the mechanism ('TTSim's physics roll (visibly lifted and spun, like pressing R)'), and distinguishes the coin/hame-face case from numeric dice. An agent can tell this apart from read_dice, which presumably only reads existing values.

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 clear operational context: roll where nothing can be hit, e.g. in a dice tray, and notes coins are flipped with randomize rather than rolled. It never explicitly says when to prefer read_dice or another sibling over this, so it stops short of naming alternatives.

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