prompt_split

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It describes the output (structured plan with agent assignments, dependency ordering, prompts), the strategy parameter's behavior, and the required user review. It does not cover authorization needs or error handling, but the core behavior is transparent.

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 concise (4 sentences, ~108 words), front-loads the main purpose, and each sentence adds value. No redundant or vague phrasing.

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 (2 parameters, no output schema), the description covers the return structure, strategy options, and usage note. It could mention potential limitations (e.g., prompt length constraints), but overall it is sufficiently complete for an agent to use correctly.

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?

Both parameters are described in the schema (100% coverage). The description adds extra meaning for the 'strategy' parameter by explaining each enum value's behavior in detail, which goes beyond the schema's minimal descriptions.

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 the tool's purpose: 'Analyze a complex prompt and split it into sub-tasks with agent assignments.' It specifies the resources involved (sub-agents like gemini, codex, openclaw, local LLM) and distinguishes from sibling tools that are execution-focused (e.g., gemini_run, codex_run).

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 implies usage for decomposing complex prompts, and includes an important guideline to 'always present the plan to the user for review before executing.' However, it does not explicitly state when to use this tool versus alternatives (e.g., directly using a run tool) or provide exclusion criteria.

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