android_screen_diff

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

Annotations already establish readOnly, idempotent, and non-destructive behavior. The description adds that the tool returns diff results (added, removed, changed nodes), which is useful. However, it does not disclose any edge cases, error conditions, or side effects beyond the basic operation.

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 a single, focused sentence with no filler. It directly states the action and expected output, making it highly efficient and easy to parse.

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?

No output schema, no parameter descriptions, and no usage context are provided. The description assumes the agent already knows what 'semantic screen snapshots' are and how to obtain the IDs. Missing details about snapshot recency or source limit the completeness.

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 does not explicitly explain fromSnapshotId and toSnapshotId. The names are somewhat self-explanatory, but no details are given about ordering, format, or how snapshots are referenced. Schema coverage is 0%, so the description carries full responsibility and falls short.

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 function: comparing two semantic screen snapshots and returning added, removed, and changed nodes. It uses a specific verb and resource, and the purpose is immediately understandable. This distinguishes it from related tools like android_screen_context or android_ui_tree.

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?

No guidance is provided about when to use this tool versus alternatives. The description does not mention conditions, prerequisites, or contrasting sibling tools. Usage must be inferred entirely from the name and brief description.

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