glass_diff

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

No annotations are provided, so the description must carry the burden. It discloses two behaviors: returns change stats + bbox, and include_image returns a cropped frame "omitted when nothing changed." However, it does not state whether the operation is read-only, how errors are handled, or how outputs change with parameters like `region` (e.g., bbox becomes region-relative). The schema provides some of this, but the description itself adds limited behavioral context.

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, front-loads the core purpose, and contains no filler. The second sentence clarifies an optional parameter's effect. Every word adds value; it is appropriately sized and structured.

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 has 7 parameters and no output schema, yet the description only vaguely says "returns change stats + bbox" without enumerating the stats fields. It does not mention the `mode`, `threshold`, `region`, or `ignore` parameters, though the schema covers those. The description is adequate for a simple diff operation but incomplete for a tool with this many options and no return type specification.

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?

Schema description coverage is 100%, and each parameter has a detailed description in the schema. The tool description only adds a note about `include_image` ("Set include_image: true to also return the current frame cropped to the changed region") and otherwise does not enhance parameter understanding. This matches the baseline of 3 for high schema coverage.

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: "Diff the current frame against a named baseline; returns change stats + bbox." It names a specific verb (diff), resource (current frame vs. baseline), and output (change stats + bbox). This distinguishes it from sibling tools like glass_baseline_save (which saves a baseline) and glass_screenshot (which captures a frame).

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 (compare the current frame to a previously saved baseline) but does not explicitly state when to use this tool versus alternatives, nor does it provide exclusions. Sibling tools like glass_wait_for_region are not mentioned in the description, though the schema references them. Guidance is implicit, not explicit.

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