select_ellipse

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

No annotations are supplied, so the description carries the full burden. It only notes "Returns status dict" and restates default values that the schema already declares; it says nothing about whether "replace" discards the current selection, what happens with a feathered edge at canvas boundaries, or whether the call fails when no image is active.

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?

Front-loaded one-line purpose followed by a tight parameter list and a return note; nothing is padded. Minor waste in restating default values already present in the schema.

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 7-parameter mutation tool with no annotations and no output schema, the description covers every parameter, the selection-combination modes, and the return type, which is enough to call it correctly. Missing only failure/edge-case behavior, which keeps it short of full completeness.

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 0% (titles only), so the description must compensate, and it partly does: it defines x/y as the bounding-box top-left, width/height as box dimensions, feather as a pixel radius, and supplies the operation enum values that the schema omits entirely. The gaps are that coordinate origin (image vs canvas), negative/out-of-bounds handling, and the accepted scale for feather remain undefined.

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?

"Create an elliptical selection" states a specific verb plus resource, which distinguishes it implicitly from draw_ellipse/fill_ellipse (drawing/painting) and from select_rectangle (shape). However, it never names an alternative explicitly, so differentiation is inferred rather than stated.

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 or when-not-to-use guidance. With siblings like select_rectangle, select_by_color, select_all, and modify_selection competing for the same intent, the description offers nothing about which to pick, no prerequisite such as an open/active image, and no note on how the operation modes interact with an existing selection.

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