classify_screen

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

With no annotations, the description carries the full burden. It discloses a key behavioral trait: it uses XML heuristics rather than an LLM, implying speed and a rule-based approach. Yet it omits potential failure modes, limitations, or side effects, though the output schema may cover return structure.

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, starting with the core purpose, then a behavioral note, and finally a usage cue. Every sentence earns its place with no padding or repetition.

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 tool is simple with only one parameter and has an output schema, so return value details are unnecessary. The description covers purpose, usage, and a key behavioral aspect. The main gap is the missing parameter explanation, but that is already penalized under parameter semantics.

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 zero description coverage for the single required parameter 'device,' and the description never mentions it. The description adds no semantic meaning beyond the schema's parameter name, leaving the agent to infer what value to pass.

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 classifies the current screen into app, screen type (home, search, profile, settings, dialog, error, loading), and keyboard state. It also differentiates from siblings by noting 'No LLM needed' and 'uses XML heuristics,' which sets it apart from OCR or accessibility-tree-based tools.

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 explicitly says 'Use this for quick state checks before deciding what action to take,' providing a clear use case. However, it does not mention specific alternatives or when not to use it, leaving the guidance slightly incomplete.

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