probabilities

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

With no annotations, the description carries the full burden of behavioral disclosure. It does not state whether the operation is read-only, mention any side effects, or disclose limitations such as stochastic behavior. While the presence of a 'seed' parameter hints at reproducibility, the description does not explicitly explain that results may vary across rollouts or that different evaluation modes have different determinism.

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?

The description is well-structured with a clear purpose line, followed by Args and Returns sections. It is concise, with no redundant sentences. Every line adds value, and the docstring format is easy to scan.

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?

The description covers all parameters and returns, but it leaves gaps. The 'evaluation_mode' options are listed without any explanation of trade-offs or suitability. Phrases like 'any supported format' for board_input are vague, and the description does not clarify the meaning of the output probabilities. Given the tool's complexity (7 params) and lack of annotations, more context is needed for full completeness.

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 schema has 0% coverage, so the description must compensate. It does so by providing a brief explanation for each of the 7 parameters, including conditions (e.g., 'player required if board_input is a boardState dict'), defaults (nr=1296, evaluation_mode='prune'), and the structure for 'score' and 'cube'. This adds meaning well beyond the bare type definitions.

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 description starts with a specific verb and resource: 'Calculate win/gammon/backgammon probabilities for a position.' This clearly states what the tool does. It does not explicitly distinguish from sibling tools like 'bearoff_probabilities', but the general scope is clear from the phrase 'for a position'.

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?

No explicit guidance is provided on when to use this tool versus alternatives. The description lacks any 'when to use' or 'use this instead of X' statements. The evaluation_mode list gives options but does not explain when each is appropriate, leaving the agent to infer usage from the tool name and sibling context.

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