take_action

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

Annotations already declare readOnlyHint=false, idempotentHint=false and openWorldHint=false, so the description is not the sole source for the safety profile. It still adds genuinely useful context beyond the annotations: actions are serialized and never retried (so failures must be handled by the caller), each call returns a fresh game state, and expected_state_id acts as an optimistic-concurrency guard against stale decisions.

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 purpose sentence, then routing, then compact examples, then the two behavioral cautions. No filler, no restatement of the name or schema, and the most decision-relevant constraint (serialized, never retried) is stated plainly.

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 29-action dispatcher with no output schema, the description covers the essentials: return payload, parameter lookup path, per-action examples, and staleness handling. It leaves the 'mode' parameter and any error/retry semantics undocumented, which the caller would have to discover elsewhere.

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 carries the burden, and it partially does: it supplies concrete payload shapes for play_card, end_turn, choose_map_node and menu_select, explains expected_state_id's purpose, and names get_action_help as the authoritative source for the remaining action parameters. The freeform 'parameters' object is otherwise undocumented, and the 'mode' enum is never explained — hence not a 5.

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?

States a specific verb and resource — 'Perform one game action and return the result plus a fresh game state' — and the return payload is named up front. It distinguishes itself from the read-only sibling get_game_state and the reference sibling get_action_help by routing explicitly to the latter for parameter names, though it never states outright that it is the sole mutation entry point.

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?

Clear context: call get_action_help for parameter names, use current state indices and target IDs, and optionally supply expected_state_id from get_game_state to reject stale decisions. That routing and the staleness precondition are actionable guidance, but there is no explicit statement of when NOT to use this tool or a named alternative for read-only inspection.

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