summarize_visual_diff

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

With no annotations, the description carries the full burden. It discloses key behavioral traits: deduplication by groupId, no image URLs/coordinates, prerequisite status, and that it does not consume credits. It stops short of error behavior or side effects, but is substantially transparent.

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 dense but each sentence earns its place, covering purpose, deduplication, output constraints, salience ordering, prerequisite, alternative, and cost. It is front-loaded with the core purpose and avoids redundancy.

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?

Despite no output schema and no annotations, the description fully specifies what the tool returns (one entry per change group with type, title, salience, snippets), what it omits (image URLs, coordinates), and when it is applicable. This is complete for an agent to decide whether to invoke it.

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 coverage is 100%, so baseline is 3. The description adds value by explaining min_salience with the prominence order and framing the tool as the cheapest way to reason about changes, which helps parameter selection. The other parameters are well-covered by 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 states a specific verb ('summarize') and resource ('visual diff of a finished visual comparison'), and clearly distinguishes from siblings by explicitly naming get_text_diff for text-mode comparisons. It also explains the unique output characteristics (page-by-page, deduplicated groups).

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 explicitly says when to use it (finished visual comparison, visual.status='ready') and when not to (text-mode comparisons, use get_text_diff instead). It also mentions it is the cheapest way, helping the agent weigh it against alternatives.

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