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

Annotations only declare the write/non-idempotent/non-destructive profile; the description adds substantial context beyond that — the server holds the board, deals and hides cards, rolls dice and enforces turns, the player gets an interactive board plus a browser link, and the agent is responsible for rules the server does not implement. The return fields (game_id, agent_key) are also disclosed despite 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?

Front-loaded with purpose, then setup options, then what the server does, then what is returned and what the agent must handle. Every sentence carries distinct information despite the density; nothing is repeated from the schema verbatim.

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 14-parameter, deeply nested creation tool with no output schema, the description covers purpose, setup shortcuts, server responsibilities, and return values — enough to call it and to chain into siblings. It stops short of stating whether repeated calls create separate games or how invalid configurations are reported, which would matter for a non-idempotent creator.

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 coverage is 79%, so most parameters are already documented in the schema (deck formats, turns modes, starter override behavior, pieces, counters). The description adds useful framing — that `starter` fields are overridable and that agent-authored rules complement server-enforced ones — but does not explain the relationship among deal/deck/dice/piles/seats beyond what the schema says.

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?

Opens with a specific verb+resource ("Set up any game to play in this chat") and scopes it across concrete game families (board, card, dice, word, mystery). It is immediately distinguishable from get_state, show_board and take_turn, which are framed later as follow-ups rather than setup.

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 two explicit paths — describe a custom game with the building blocks, or pass `starter` for a ready-made one — and enumerates all twelve starters so no lookup is needed. It also states the sequencing contract: keep game_id and agent_key for get_state and take_turn, which names the alternatives and when to move to them.

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