customize_on_phone

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

The description outlines the main behavior: send control, user edits via phone, then return the shaped control. It mentions the side effect of add_to_buffer and the requirement for a live-edit session. However, it does not cover error handling, timeout behavior, or what happens if the user cancels. With no annotations, the description carries the burden and does a reasonable job.

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: a clear opening statement, a memorable guiding phrase, a note on prerequisites, and a bulleted Args list. Every sentence contributes value, and the critical info is front-loaded.

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 explains the tool's flow, prerequisites, and side effects well. It notes that the output is the shaped control, but does not detail the output format; however, the presence of an output schema (confirmed in context) mitigates this. Some missing details (e.g., timeout behavior when exceeded) keep it from perfect completeness.

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?

Since input schema has 0% description coverage, the description provides essential parameter details: control_json with an example, timeout with default, add_to_buffer explaining its effect, and tab_index context. This adds significant meaning beyond the raw schema, making it easy for an agent to understand how to use each parameter.

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's purpose: to hand off a control to a phone for human customization via live preview and field editor, then read back the result. It uses specific verbs ('hand', 'customize', 'read back') and distinguishes itself from sibling tools like add_control or update_control by emphasizing the interactive human role.

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 implies usage context: when you want the user to manually customize a control. It includes a prerequisite ('requires a paired device in a live-edit session') and a mantra ('shape it on glass, wire it on the model'). However, it does not explicitly state when not to use this tool or mention alternatives, but the context is sufficiently clear.

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