classify_screen

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

Beyond the read-only annotation, the description discloses mode-dependent behavior (server-side versus on-device gates), credential requirements, and return shapes. This adds meaningful context about how the tool behaves in different configurations, though not every edge case is covered.

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: purpose first, then behavior, then return shapes in bullet form. Every sentence contributes new information, and it avoids repetition or filler.

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 no output schema, it explains the two possible return types (dict and fallback list) and the fallback classification instructions. However, it omits parameter meaning and specific phase fields, leaving some gaps for a tool with optional params.

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 schema has two parameters (hint, profile) with zero description coverage. The tool description does not mention or explain either parameter, so it adds no semantic value. With 0% coverage, the description was expected to compensate but did not.

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 starts with a specific verb and object: 'Classify the current screen's boot/run phase', making the purpose clear and distinct from sibling tools like boot_options or power_state. It also adds the 'read-only' qualifier, reinforcing scope.

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: it states it classifies boot/run phase and explains two modes (server-side vs on-device gates) with credential implications. It does not explicitly name alternatives or exclusions, but the usage context is strong.

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