ui_diff

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

With no annotations provided, the description carries the full burden. It discloses that the diff is semantic and that it defaults to the last snapshot, and mentions the server keeps 5 snapshots. However, it does not describe the output format (e.g., list of changes, text), or mention idempotency, side effects, or what happens if no snapshot exists. More behavioral detail would be helpful.

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 two sentences long with no wasted words. It is front-loaded with the core purpose and provides key context in a concise manner.

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?

Given no output schema, the description should hint at the return value. It says 'answers what changed' but does not specify whether the output is a structured diff, text, or list. Missing details on prerequisites (e.g., a snapshot must exist) and error handling. With sibling tools, the overall purpose is clear, but completeness is adequate but not thorough.

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?

Both parameters are documented in the schema (100% coverage), and the description adds value by specifying the default snapshot behavior ('default: the last one this server took') and the condition for device ('when exactly one device is booted'). This goes beyond the schema descriptions.

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 it computes a semantic diff between the current UI and a previous snapshot, and explicitly says it answers 'what changed?' without comparing screenshots. This distinguishes it from sibling tools like screenshot and get_ui_tree, and the verb 'diff' combined with the resource 'UI' makes the purpose specific.

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 implies usage for detecting UI changes programmatically, but does not provide explicit guidance on when to use this tool versus alternatives like get_ui_tree or screenshot. There are no when-not-to-use statements or comparisons with siblings.

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