debug_screen

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

No annotations are provided, so the description carries the full behavioral burden. It implies a diagnostic read operation by mentioning an observation snapshot, but it does not state side effects, permissions, rate limits, or whether candidate actions are executed.

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 compact and front-loads the purpose and return shape before the argument note. Every clause carries information, with no redundant wording.

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 and no annotations, the description leaves 'observation snapshot' and 'candidate action list' underspecified. It is enough to identify a diagnostic tool, but not enough to interpret the return or confidently choose it over sibling screen-related tools.

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 declares zero properties, but the description adds an optional goal argument with a default of '打开设置'. That adds useful meaning beyond the schema, though it does not explain how goal affects the returned snapshot or candidates.

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 names the resource it returns—an observation snapshot plus candidate actions—and frames it as a troubleshooting tool. It does not distinguish it from screen, mini_screen_status, or ACTION_READ_SCREEN, so a 4 is appropriate rather than 5.

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?

It says only '排查用' (for troubleshooting), which gives an implied usage context. It provides no explicit when/when-not guidance and names no alternatives such as screen or ACTION_READ_SCREEN.

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