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

Annotations declare the safety profile (non-read-only, non-destructive), and the description adds real behavioral context beyond them: the returned value is your view of the session, the waiting/null-state window, and the Pips economics of a stakes table. It doesn't cover failure modes or what happens if you're already seated in a session.

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 core action comes first and the multiplayer follow-up is front-loaded right behind it, with the Lucky Hand special case last. Dense but every clause carries behavior; the nested clauses make it slightly harder to scan than it needs to be.

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?

With no output schema, the description carries the return-value burden and does so loosely ("your view of the session") while filling the more important gap — the waiting state that dictates the next call. Missing only failure/edge behavior such as already being in a session.

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 documents game (with an example and a pointer to list_games) but stake has no description at all, only a 20/50 const. The description compensates fully: stake is Lucky Hand only, each player pays that many Pips, and the most chips takes the pot.

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?

"Starts a session" gives a specific verb and resource, then immediately scopes it: multiplayer seating vs. Lucky Hand stakes tables. An agent can distinguish this from get_session or wait_for_turn because the description names the follow-up tool and the waiting-seat state. It doesn't explicitly contrast with get_session/leave_game, so it falls short of a clean 5.

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?

Explicit conditional guidance: if the game is multiplayer and seats remain open, status is "waiting" and state is null, so call wait_for_turn. It also restricts the stake parameter to Lucky Hand. It stops short of saying when NOT to call start_game (e.g. resuming via get_session).

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