shelly_scene_create

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

Annotations provide idempotentHint=true; the description adds requirements for methods and devices, failure conditions, and a warning about Toggle methods. This adds significant context beyond the annotation, revealing safe usage patterns.

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 (3 sentences) and front-loads the purpose. Every sentence adds value, but could be better structured (e.g., separate constraints from advice). No wasted words.

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 complexity (4 params, 2 required) and presence of an output schema, the description covers the essential behavioral aspects: action structure, method constraints, overwrite behavior. It does not mention return values (covered by output schema) or rate limits. Minor gap for 'description' parameter.

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?

With 0% schema coverage, the description compensates by explaining the structure of 'actions' as ordered list of device/method/params and the meaning of 'overwrite'. It does not describe 'name' (obvious) or 'description' (minor gap). Overall adds substantial meaning beyond the bare 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 defines/saves a named scene from an ordered list of actions, which is a specific verb+resource. It distinguishes itself from sibling scene tools (run, delete, get, list) by focusing on creation. The structure of actions is also explained.

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 explicit constraints: methods must be non-destructive mutating, devices must be known, overwrite behavior for existing names, and a preference for Set methods over Toggle. It gives clear context but does not explicitly compare to alternative scene creation tools (none exist) or state when not to use.

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