scan_unique_images

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

With no annotations provided, the description carries the full disclosure burden. It reveals that the scan covers every string field in the source tree (config.src, style.background-image, etc.) and CSS url(...) references, including a 'wide net catches all variants' caveat—genuine behavioral insight beyond the schema. It does not explicitly state side-effect freedom (e.g., read-only), but the scanning nature and return description make the read-only behavior implicit.

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?

Three tight sentences: first states the action and output, second gives use cases, third explains the technical scanning behavior. No filler or 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?

Given the absence of an output schema, the description still explains the return value as a unique list of image URLs with element usage. It also clarifies the broad scanning behavior and lists practical use cases, making the tool's behavior easily predictable.

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?

All four parameters are fully described in the schema (100% coverage), giving a baseline of 3. The description adds no extra parameter-specific guidance beyond noting the output shape, which does not go beyond the schema's parameter documentation.

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 opens with a specific verb 'Scan' and names the exact resources (page sources, global sources, global sections) and the return behavior (a unique list of image URLs with element usage). This clearly distinguishes it from sibling tools like search_images or list_image_elements, which focus on search or element listing rather than cross-source auditing.

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 lists four concrete use cases (image audit, finding broken/duplicated CDN URLs, bulk replace planning, theme migration), giving clear context for when to invoke it. It does not name alternatives or exclusions, so it stops at 4 rather than 5.

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