get_screen_state

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

No annotations are supplied, so the description carries the full burden. 'Get ... state' reasonably implies a read-only, side-effect-free inspection, and the enumerated fields tell the agent what it will learn, but it does not confirm the operation is non-mutating, note cost, or say whether state is captured live or cached.

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?

A single front-loaded sentence naming the verb and resource first, with the return contents listed as a compact colon-delimited clause. No filler, no restatement of the name.

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?

With no output schema, the description must communicate the return shape, and it does so by enumerating the five state facets. With zero parameters and a simple read operation, that is nearly sufficient; only the live-vs-cached nature of the state remains unspecified.

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 tool takes zero parameters, so the baseline is 4. There is nothing for the description to disambiguate, and it correctly adds no misleading parameter talk.

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?

States a specific verb ('Get') and resource ('screen manager state'), then enumerates the exact facets returned: mode, active screens, transition status, pause state, element/interactive counts. It implicitly separates itself from list_screens (which enumerates screens) by focusing on aggregate state, though it never names a sibling explicitly.

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?

There is no guidance on when to call this versus list_screens, scene_graph, or get_tween_state, and no stated preconditions such as requiring an active connection. The agent must infer the diagnostic use case from the field list alone.

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