draft_skill

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

With no annotations, the description carries the full burden. It explicitly states 'Nothing is written', making the side-effect-free nature clear. It also discloses the return contents (steps, app_package, summary) and instructs the user to review/prune/rename, which adds behavioral context beyond a simple 'draft' label. Missing details like error handling or prerequisites prevent a 5.

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, front-loaded with the main action, and every sentence adds value: purpose, return value, and side-effect/next-step. No filler or repetition of schema data.

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?

For a tool with one simple parameter, no annotations, and an output schema, the description provides a solid overview of functionality, side effects, and next steps. It lacks a bit of context about what a 'HARD skill' is and assumes the agent knows the workflow, but overall it is complete enough for its simplicity.

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?

Schema coverage is 0% for the only parameter 'device'. The description mentions 'device's most recent chat conversation', which gives some context that the parameter identifies the device, but it does not explain the expected format (e.g., device ID vs name). Since the parameter name is self-explanatory, baseline would be 3; the description adds minimal extra meaning.

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?

Description uses specific verb 'distil' and clearly identifies the resource: the device's most recent chat conversation, output as draft replayable steps for a HARD skill. It distinguishes from sibling save_skill by stating 'Nothing is written' and pointing to save_skill as the subsequent step.

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 clearly indicates the workflow: generate draft steps with this tool, then call save_skill(kind="hard", steps=...). This effectively tells the agent when to use it (before saving a skill) and implies the alternative (save_skill) is for the actual saving. However, it does not explicitly state when not to use it or mention edge cases like no conversation history.

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