decompose_plan

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

With no annotations provided, the description carries the full behavioral burden and does so thoroughly. It discloses the success and failure return contracts, includes raw output on parse failures, states that it never raises, and clarifies that it does not persist the plan via save_plan.

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 longer than average, but every paragraph serves a distinct decision point: core action, provider configuration, relationship to the alternative path, save_plan responsibility, and return contract. The main purpose is front-loaded in the first sentence, and there is no obvious filler.

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 one parameter, no annotations, and the complexity of provider selection and output handling, the description is complete. It tells the agent exactly what to pass, what provider will be used, what the return shape is, what failure looks like, and what the agent must do after calling 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?

The schema has 0% description coverage, so the description must define the sole request parameter. It does this by calling it a 'raw goal/feature request', which is sufficient for a single free-form string parameter, though it does not give examples or length/format constraints.

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 a specific verb-resource pair: 'Turn a raw goal/feature request into epics/stories JSON'. It further distinguishes itself from the interactive product-analyst subagent and clarifies that it is a separate decomposition path, so an agent can tell it apart from siblings like save_plan and the Agent tool.

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 explicitly explains when to use this tool versus the interactive product-analyst subagent: the interactive path is still the default for Claude-quality decomposition, while this tool is for running decomposition on a local provider when desired. It also gives a clear behavioral instruction: do not expect it to call save_plan; review the output and save it yourself.

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