best_move

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

With no annotations, the description carries full responsibility for behavioral disclosure. It mentions the neural network evaluation method, the trade-off for ply depth, seed for reproducibility (implying potential randomness), and outlines the return structure including alternatives with probabilities. This adds meaningful context beyond the schema, though it doesn't explicitly state side-effect-free behavior or error conditions.

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 efficiently structured: a one-sentence purpose, a clean Args list, and a Returns line. Every sentence adds value, and the front-loaded first sentence immediately tells the agent what the tool does. The format is easy to parse and not padded.

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 tool with 7 parameters, no annotations, but an output schema, the description is complete. It covers purpose, all parameter semantics, and a high-level return description (leaving detailed return parsing to the output schema). The only gap is explicit sibling differentiation, but that is a minor omission given the clear purpose and parameter detail.

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 fully compensate. The Args section explains each of the 7 parameters: board_input accepts any supported format, dice format, player default, ply meaning, match score context, cube state structure, and seed purpose. This adds rich semantic meaning beyond the plain schema types and defaults.

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 opens with a specific action and resource: 'Find the best move for a position and dice roll using neural network evaluation.' This precisely states what the tool does and distinguishes it from siblings like pub_best_move or moves by focusing on the best-move computation. The 'Returns' section further clarifies the output, reinforcing purpose clarity.

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 description provides context for parameter choices (e.g., 'ply: Higher is stronger but slower', 'score: Omit for money game') but does not explicitly state when to use this tool over siblings like pub_best_move or when to avoid it. The usage is implied through the tool's purpose rather than explicitly differentiated.

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