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

Goes beyond the readOnly/idempotent annotations by disclosing a key behavioral trait: you see only your own cards, never anyone else's, and keyless/shadow observers see the board but no hole cards. That is real visibility/permission context an agent could not infer from annotations. It does not cover error behavior for a bad or expired table id.

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 sentences, front-loaded with the verb and the returned fields, then the access rule. Dense but every clause carries information; the card-visibility caveat is properly appended rather than buried.

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 read-only, idempotent view with no output schema, the description carries the return-value burden well by enumerating the observable state, and annotations cover the safety profile. Slightly incomplete on what happens with an invalid table id or on how time-until-turn is expressed.

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 100%, so the per-parameter text already defines `table`, `key`, and `shadow`; the baseline would be 3. The description adds meaning the schema lacks by tying the keyless (`shadow`) path to a visible consequence — no cards but the board — which clarifies what selecting that parameter path costs.

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 ("See a table") and enumerates exactly what is visible: seats, stacks, bets, board, pots, turn and clock, own cards, and next-hand commitment. An agent can tell this is the per-table state view, but it never names or distinguishes itself from close siblings such as `tables` (the lobby), `board`, `hand`, or `look`, leaving the boundary implicit.

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 one concrete access rule, "Anyone may watch without a key, as a shadow does," which explains the unauthenticated path, but offers no explicit when-to-use or when-not guidance against the many sibling read tools. Usage is implied rather than routed.

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