save_skill

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

With no annotations, the description carries the full burden. It explains the two modes (hard/soft), the auto-distillation behavior when steps are omitted, and how soft skills are surfaced to agents. This goes beyond simply saying 'save' and provides meaningful behavioral context, though it does not mention potential overwrites or permission requirements.

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 and well-structured. The first sentence states the core purpose, and the second sentence efficiently explains both modes and related tools without any redundant phrasing. Every clause adds value.

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?

The description covers the essential behaviors for both hard and soft skills, references related tools, and clarifies the significance of steps and guidance. Given that an output schema exists, return values need not be described. Minor gaps remain around prerequisites (e.g., an active conversation) and naming conflicts, but the overall context is sufficient for an agent.

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 description adds significant meaning to key parameters: it explains that steps is a JSON array from draft_skill, kind distinguishes between hard and soft, and guidance is markdown. This is valuable given the 0% schema coverage. Other parameters like name and device are self-explanatory, and app_package/description are left for inference.

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 states a specific verb and resource: 'Save the device's current chat conversation as a reusable skill.' This clearly differentiates it from sibling tools like create_skill, which implies creating a skill from scratch, and draft_skill, which is mentioned as a source for steps.

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 gives clear guidance for using hard vs soft modes and references draft_skill and list_skills/run_workflow as related tools. However, it does not explicitly compare save_skill with alternatives like create_skill, nor does it state when not to use this tool, so the guidance is implied rather than fully explicit.

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