send_to_back

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

No annotations are provided, so the description carries the full burden. It discloses the exact z-order calculation ('z = current min - 1'), which is a concrete behavioral detail. It does not mention side effects like undo behavior or whether the visual is moved within a specific page, but for a simple z-order operation, this is reasonably 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 a single, efficient sentence that leads with the action and includes a helpful example. Every word earns its place, with no filler or redundant content.

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 low complexity of the operation (send a visual to back), no output schema, and only 3 simple parameters, the description is nearly complete. It explains the effect and provides an example, though it does not address error cases or prerequisites (e.g., visual must exist on the page). However, these are likely standard assumptions for such a tool.

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 67% (page and visual are described, reportSessionId is not). The description adds no direct parameter semantics beyond what the schema already provides; it only mentions 'a visual' generically. Baseline 3 is appropriate because the schema covers most parameters, but the description does not compensate for the undocumented reportSessionId.

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 uses a specific verb 'Send' with a clear resource ('a visual') and a clear outcome ('to the BACK of the page'), and it distinguishes itself from sibling tools like 'bring_to_front' by the direction. The z-order formula ('z = current min - 1') adds precision.

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 example 'push a decorative panel behind the data visuals' provides clear usage context, implying when to use this tool (to place an object behind others). It does not explicitly state when not to use it or name alternatives (like 'bring_to_front'), so it misses the highest bar.

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