cmmn-execute_stage

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

With no annotations, the description fully discloses key behaviors: depth-first traversal, human task pausing, and the requirement for the LLM to process llm_execute actions immediately. It also clarifies that the stage is not complete until all such actions are handled.

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 well-structured with a clear core action and an IMPORTANT section for critical instructions. It is slightly verbose but all sentences add value. Could be more concise but remains effective.

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?

Covers main behaviors but lacks details about the return structure (no output schema), error conditions, and behavior for different human_task_mode values. The description implies a result structure but doesn't fully explain it.

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 100%, so the baseline is 3. The description adds minimal parameter context beyond what the schema provides (e.g., implying default for human_task_mode). No additional details for max_depth, max_items, or context.

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 clearly states it executes a stage via depth-first traversal, which is specific. It differentiates from siblings like cmmn-execute_task through the mention of stage versus task, but does not explicitly contrast with other related tools.

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?

Provides explicit instructions for handling llm_execute actions and when to call cmmn-complete_task. However, it does not specify when not to use this tool (e.g., for individual task execution) or mention alternative tools like cmmn-execute_task.

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