control_state

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

No annotations exist, so the description carries the full behavioral burden. 'Get' signals a read, and the enumeration of fields tells the agent what data arrives, but it omits session/auth preconditions, whether the call is cheap enough to poll, and any note about side effects or timing.

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?

A single front-loaded sentence that leads with the verb and the resource, then lists contents in a compact, scannable order. No filler, no restatement of the tool name.

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 is the only source of return-value information, and it lists top-level contents but not their shape — 'card details' and 'pending prompt counters' are left undefined for a nested state object. It is adequate to know when to call it, but thin for parsing the response.

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 tool takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. No parameter-level confusion is possible with an empty, additionalProperties:false schema.

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?

Specific verb ('Get') plus a concrete resource ('full duel state') with an enumerated payload: turn, phase, LP, hand/field/grave/deck counts, card details, pending prompt counters. It is clearly a state-snapshot reader, distinguishable in spirit from siblings like control_actions or control_lobby, but it never names or contrasts those siblings explicitly.

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?

There is no when-to-use or when-not-to-use guidance, no mention of alternatives (e.g., control_actions for legal moves, control_wait_prompt for blocking on input), and no prerequisites such as needing to be in an active duel. Usage is only inferable from the returned payload.

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