build_control_variable

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

With no annotations provided, the description carries full responsibility for behavioral disclosure. It explicitly states 'Read-only: returns { command }', which reveals that the tool has no side effects and only returns a data structure. It also clarifies that the command is meant for insertion via insert_event_commands, implying it does not automatically apply changes. This goes beyond what the schema or annotations would provide.

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 description is two sentences, front-loaded with the primary purpose, and every piece of information contributes to understanding the tool's function. It avoids repetition of schema fields and wastes no words.

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?

Given the tool's complexity (nested operand object, 5 parameters, no output schema), the description covers the core behavior, return shape, range semantics, and operand categories. It does not explain how to configure game_data parameters in detail, but that is partially handled by the schema and the 'see corescript' hint. Overall, it provides sufficient context for an agent to use the tool correctly in the majority of cases.

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 parameters are already documented. The description adds valuable semantics by explaining the inclusive variableId..endId range behavior, the supported operation types (set/add/sub/mul/div/mod), and the four operand sources (constant, variable, random, game_data). This exceeds the baseline and helps the agent map high-level intent to schema fields. Minor gap: game_data sub-parameters are not detailed in the description, but the schema references 'corescript'.

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?

The description uses a specific verb ('Build') with a concrete resource ('Control Variables (122) event command') and explicitly states its purpose ('for insertion via insert_event_commands'). This clearly distinguishes it from sibling builder tools like build_show_text or build_conditional_branch, which target different event command types.

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 description provides clear context: this tool constructs a command for later insertion via insert_event_commands. It implies the tool should be used to prepare a command rather than directly modify the game. However, it does not explicitly mention when not to use it or name alternative tools for similar operations (e.g., build_control_switch for switches).

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