control_actions

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

No annotations are supplied, so the description carries the full load. It does add real behavioral value by clarifying that this tool is a lookup only and that the client handles encoding the kernel response, which prevents an agent from trying to build a payload. It stops short of stating error/empty-prompt behavior or whether the list is stable between calls.

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 resource, and the parenthetical example list is compact and informative rather than padding. The second sentence is slightly cryptic ("kernel response") but earns its place by explaining the division of labor.

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 parameters and no output schema, the description correctly compensates by describing the returned fields and giving example action kinds. Missing only edge-case behavior when no prompt is active, which is minor for a simple enumeration tool.

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 defines zero parameters, so there is nothing to disambiguate; baseline 4 applies. The description does not waste space re-explaining an empty input object.

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 plus resource: "List the semantic actions available for the current prompt," with the return shape spelled out (id + kind + human label) and concrete enum-like examples (summon/special summon/attack/chain/zone). It implicitly separates itself from control_act/control_act_id by saying the caller only picks an id, but it never names 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?

"The caller only picks an id; the client encodes the kernel response itself" implies the discover-then-act flow with control_act_id, but the description never states when to call this versus control_state or control_act_id directly. There are no exclusions or preconditions (e.g., what happens when no prompt is pending).

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