create_skill

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

With no annotations, the description carries the full burden and does well: it reveals the input format, supported actions, iOS-specific parameter handling, and side effect of writing elements files (elements_ios.yaml/elements.yaml). It does not mention overwrite behavior or error conditions, but the disclosed details are substantial. Minor confusion around app_package vs ios_bundle_id in iOS case slightly detracts.

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 well-structured: a purpose sentence, a JSON example, supported actions, iOS handling, optional elements, and a follow-up command. It is somewhat long but every part provides necessary information without waste.

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 7 parameters and platform nuances, the description covers key aspects: creation, step format, action types, iOS platform handling, optional element maps, and the replay workflow. It omits details about return values, but the presence of an output schema reduces that need. Missing overwrite or error behavior prevents 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?

Schema description coverage is 0%, so the description must compensate. It thoroughly explains the `steps` parameter with an example, and gives meaning to `platforms`, `app_package`, `ios_bundle_id`, `elements_ios`, and `elements_android`. However, `name` is never described, and the wording 'either app_package or ios_bundle_id' is ambiguous given that `app_package` is required.

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: 'Create a new reusable skill from a JSON list of recorded steps.' It clearly distinguishes from siblings like run_workflow (replay) and draft_skill, and provides a concrete example.

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?

Provides clear context on when to use the tool (creating skills from recorded steps) and explicitly instructs the follow-up: 'After creating, use run_workflow(dev, name, "recorded", params) to replay it.' It also gives platform-specific guidance for iOS. However, it does not explicitly mention alternatives or 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.