ui_checkpoint

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool 'remembers the current screen' but does not disclose side effects, whether it is read-only, what happens to previous checkpoints, or what the output is. It gives minimal behavioral context beyond the core action, which is inadequate for a tool without annotation safety hints.

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. It leads with the purpose, then gives a usage example, then lists arguments in a clear format. Every sentence serves a purpose, and it is front-loaded with the most important information. There is no 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 simple checkpoint tool with optional parameters and an output schema (though not detailed), the description is reasonably complete. It explains when to use it (before code edits), what it does (remembers screen), and how to parameterize it. It doesn't describe the return value, but the presence of an output schema means the description needn't explain that. Minor gaps like preconditions (e.g., device attached) are not critical given the sibling context.

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 explicitly explains both parameters: 'label: name for this checkpoint' and 'serial: device serial when several are attached.' This adds meaning beyond the schema, which only provides types and defaults. Since schema description coverage is 0%, the description compensates well by explaining each parameter's purpose.

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: 'Remember the current screen so a later ui_diff can show what changed.' This is a specific verb (remember) and resource (current screen), and it distinguishes from ui_diff by explaining the relationship. It is not a tautology and gives a clear mental model.

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 a usage pattern: 'Take one before editing code, then call ui_diff after hot reloading.' This gives a clear context and sequencing, and implicitly tells the agent to use it before code edits and ui_diff after reload. It doesn't explicitly state when not to use it or name alternatives, but the workflow is clear and sufficient for a simple tool.

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