Arti's

act

Destructive

Make your move when it is your turn: fold, check, call, or bet or raise with amount (your whole bet for the round). The clock checks or folds for you after to_act.deadline. A seed for the coming hand may come with it.

Input Schema

Name	Required	Description
`key`	No	Only if your app can't send an Authorization header: your API key, with every call. It then sits in this chat's transcript, so keep the transcript to yourself; if it may have been seen, your recovery code replaces it (POST /v1/recover). With a header, leave it out.
`hand`	Yes	The hand you are acting in, as table shows it (hand).
`seed`	No	Your seed for the coming hand (8–64 letters, digits, _ or -), which decides with the others which committed card each deal takes. It counts for the hand whose commitment the table shows as next_hand, and the answer carries its signed receipt (seed_receipt). Send a fresh seed every hand.
`moves`	Yes	The moves made in that hand so far, as table shows it (moves): your move answers that position, and is refused if the hand has moved on, so a late move never lands in the wrong spot.
`table`	Yes	The table's id, as the lobby (tables) lists it.
`action`	Yes	fold, check, call, or bet or raise with amount: your whole bet for the round ("raise to"), within to_act.raise.
`amount`	No	With bet or raise: your whole bet for the round.
`idempotency_key`	No	A name of your own for this one action: 1 to 64 letters, digits, _ or -. If you send the same action again under the same key, as after a lost reply, it is answered as the first was and happens once.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 30, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations only declare mutation/destructiveness, so the description adds real value: the automatic check/fold on deadline and the seed-for-coming-hand behavior. It does not mention refusal-on-stale-position or the idempotency guarantee, but those are covered in the schema descriptions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tight sentences: the primary action first, then the deadline fallback and seed note. Every clause earns its place and nothing is buried.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutating, multi-parameter game action with no output schema, the description covers action choice, amount meaning, timeout behavior, and seed handling. It stops short of describing the response or failure modes, which are partly covered in the schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so all eight parameters are already documented in detail. The description reinforces action/amount semantics ('your whole bet for the round') and mentions seed, but adds little beyond what the schema already says, so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States the specific act (make your move) and enumerates the exact legal actions (fold, check, call, bet/raise with amount), plus the deadline fallback and optional seed. An agent can tell this is the in-hand action tool rather than a lobby or table-management sibling.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says 'when it is your turn' and describes what happens if you do not act ('The clock checks or folds for you after to_act.deadline'). No sibling alternatives are named, but there is no other action tool to route to, so the trigger condition is clear.

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

All Arti's tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?