add_rule

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

With no annotations, the description must carry the behavioral burden. It discloses two useful behaviors: invalid code is rejected with line/column errors, and legacy structured fields are still accepted. However, it does not mention whether the tool mutates state, whether there are side effects, or any permission requirements. Given the lack of annotations, this is a partial disclosure.

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 about 100 words, front-loaded with the core purpose and then providing examples and error handling. Each sentence contributes unique information: syntax, examples, and error/rejection behavior. It is structured well with code blocks, though slightly dense.

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?

The tool has 21 parameters, three required, and no annotations. The description covers the core code-based usage and error behavior, and mentions legacy fields, but does not explain the overall context of rules (e.g., trigger/effect relationship, execution order, or how owner_actor_id and target_actor_id work). Given the complexity and lack of annotation support, the description is not fully complete, though it provides a solid starting point.

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 description coverage is 0%, so the description is the only source of parameter meaning. It effectively explains condition_code and effect_code with syntax examples, and hints at 'action' with ACTION6 coordinates. However, many legacy parameters (owner_actor_id, source_actor_id, condition_operator, etc.) are not explained. The description adds value but does not fully compensate for the low schema coverage.

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 opens with 'Attach actor ECE code', clearly identifying the tool's verb and resource. This distinguishes it from sibling tools like add_collision_effect or add_timer_effect, which target specific effect types. However, the term 'ECE code' is somewhat technical and may require prior context to fully understand.

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 concrete usage patterns through examples of condition_code and effect_code syntax. It implies this is the modern approach ('Legacy structured fields remain accepted'), but does not explicitly state when to choose this over sibling tools or when not to use it. No alternative tools are mentioned.

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