decompose_flutter_prompt

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

No annotations are provided, so the description must carry the behavioral info. It discloses the 'always checks and verifies target platforms first' behavioraine. However, it doesn't mention potential side effects, authentication requirements, or what happens when the prompt can't be decomposed (e.g., ambiguous input), nor the output format. The behavior disclosed is minimal and could be more informative, such as noting that a clarification might be sent back if a target platform is unspecified.

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 compact at two sentenceshol and front-loads the key action ('Deconstructs Flutter prompts'). The second sentence adds a behavioral guidance (target platform check) that is useful and efficiently phrased. No wasted words, though the two clauses could be separated for clarity, but it's still pretty crisp.

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 (producing features, modules, sprint plans) and lack of an output schema, the description conveys what class of output is expected (features, modules, sprint plans) but not the format. It also hints at the conditional logic for target platforms. For a planning tool that returns a structured plan, the description is relatively complete for an agent to decide when to call itate it, but doesn't specify the output structure, which lowers it from a 5.

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 input schema has descriptions for all five parameters, including the targetPlatforms array which is explicitly 'if not provided or mentioned in prompt, a clarification is returned' (this is in the schema description). The tool description adds marginal value about the parameters; it doesn't explain the 'sprint plans' output or how architecturePattern affects results. With essentially 100% schema coverage, the baseline of 3 is appropriate, and the description doesn't go beyond the schema.

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: deconstructs Flutter prompts into Clean Architecture features, modules, and sprint plans. The verb 'deconstructs' is specific skill (planning/decomposition) and the resource 'Flutter prompts' is identified where it comes from. This distinguishes it from sibling tools like scaffold_flutter_backend or generate_flutter_tests, which are about execution rather than planning.

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 states the tool always checks and verifies target platforms first, which is a clear usage hint. It doesn't explicitly state when to use this tool instead of siblings, but the purpose is clean enough for an agent to infer it should be called when a user provides a high-level prompt to break down. No explicit exclusions are given, but the context is sufficiently portrayed.

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