create_or_reset_game

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

With no annotations provided, the description carries the full burden of disclosing behavior. It thoroughly details the return structure (ok, status, moves, moves_detailed) and explicitly states the reset behavior (empty moves array after reset). It also clarifies the tool's non-advisory scope, adding meaningful context beyond simple 'resets game.'

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-organized: a one-sentence purpose statement, followed by a structured list of return fields. While the list is lengthy, each item adds semantic value (e.g., explaining castling rights and en passant notation). It could be trimmed if the output schema already covers these details, but the description remains efficient and front-loaded.

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 zero-parameter, state-manipulation tool with no annotations, the description is exceptionally complete. It explains the full return payload, the reset semantics, and the tool's scope ('does not suggest moves'). It leaves no ambiguity about what happens when invoked and what information the caller receives.

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 has zero parameters, so the schema requires no explanation. Per the rubric, a baseline of 4 is appropriate for 0-parameter tools. The description adds no parameter-specific semantics because none are needed, and it doesn't mislead about inputs.

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 'Create a new game or reset the current one to the initial position,' which is a specific verb+resource statement. It clearly distinguishes itself from siblings like add_move or get_status by focusing on state initialization/reset, and reinforces this with the note that it does not suggest moves.

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 includes the note 'This tool does not suggest moves; it only manages state,' which provides a clear exclusion and implied usage context. While it doesn't explicitly name alternatives like get_status for queries, the sibling list and the tool's own purpose make the appropriate use case clear.

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