share_thoughtStream or update your internal companion thinking bubble on the board. This appears live to your human as a thinking bubble above your avatar.
| Name | Required | Description | Default |
|---|---|---|---|
| game_id | Yes | ||
| thought | Yes | Your internal thought, reaction, or calculation note (1-2 sentences). | |
| is_typing | No | Whether you are actively calculating or drafting a response. | |
| agent_token | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does disclose the key side effect: the thought appears live and is visible to the human above the avatar. It does not say whether the thought is replaced or updated, how long it persists, or any rate or visibility constraints.
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?
Two tight sentences with no filler. The action and target are front-loaded, and the second sentence adds the essential live-visibility consequence.
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 4-parameter companion tool, the description covers what the tool does and its core visible effect. It lacks an explicit pointer to send_chat as the alternative for real conversation, but schema definitions carry the parameter details, so the overall context is sufficient.
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 already documents thought and is_typing, so the description adds little parameter-level meaning beyond the 'thinking bubble' context. game_id and agent_token remain undocumented and the description doesn't clarify their purpose or format.
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 names a specific action ('Stream or update') and a concrete resource (the 'internal companion thinking bubble'), and the second sentence grounds it as a live bubble above the avatar. This clearly distinguishes it from send_chat and react_to_chat.
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 implies when to use it: whenever the agent wants to expose an internal thought live to the human. However, it never names an alternative like send_chat or says when not to use it, so the routing decision is left to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct action or resource: game lifecycle, board queries, move execution, chat/reactions, draw handling, and event waiting. The only near-neighbors — get_game_state vs get_legal_moves and offer_draw vs respond_to_draw — are clearly separated by their descriptions.
The set overwhelmingly follows a verb_noun snake_case pattern like create_game, get_game_state, and send_chat. Two single-word exceptions, heartbeat and resign, deviate slightly but remain clear and unlikely to cause confusion.
14 tools is well within the ideal range and each one covers a concrete need: setup, state, moves, communication, presence, and event handling. There are no redundant tools or filler entries.
The surface covers the full game lifecycle: create/join, legal moves, move execution, draw offer/response, resignation, and chat/reactions. The wait_for_event loop ties the asynchronous experience together, and get_game_state includes move and chat history, so no major gap is apparent.