get_selection_bounds

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

No annotations exist, so the description carries the full burden. It does disclose the return shape ({has_selection, x, y, width, height}), which tells the agent how to detect an empty selection, but it omits units (assumed pixels), coordinate origin, and what x/y/width/height contain when has_selection is false.

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 definition is short, front-loaded with the purpose, and cleanly split into Parameters and Returns blocks with no filler. The parameter line largely duplicates the schema's default value, but the overall size is appropriate for a one-parameter read tool.

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?

For a simple read-only geometry query with no output schema, returning the field list inline is the right move. However, the absence of any statement about no-selection behavior, pixel units, or multi-image indexing leaves gaps an agent would likely hit in practice.

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 0%, so the description must compensate for the single parameter. It restates image_index with its default of 0 but never explains what an image index refers to (an index into list_images) or how it relates to set_active_image, leaving the parameter only partially meaningful.

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 first sentence states a specific verb and resource: reading the bounding rectangle of the current selection. An agent can tell it apart from mutating selection tools like select_rectangle or modify_selection, though the description never names a sibling explicitly.

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?

There is no when-to-use guidance, no prerequisites, and no mention of alternatives such as get_image_metadata or get_context_state that might also expose geometry state. The agent must infer that this is a pre-flight read before crop_to_selection or crop_to_rect.

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