imgui_update_hit_region

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

No annotations are provided, so the description carries the full behavioral disclosure burden. The partial-update semantic ('Only provided fields are updated') is a valuable behavioral disclosure. However, it doesn't disclose what happens with invalid ids, whether the hit region's other attributes not in the schema are affected, whether this triggers a redraw/re-render, or any constraints on combining p1/p2/points simultaneously.

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 appropriately concise at one sentence and clearly front-loads the purpose. The key partial-update semantic is packed into a short second sentence. It could arguably be condensed, but the two-sentence structure earns its keep by adding the 'only provided fields' clarification. No wasted words.

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 tool with 6 parameters, 0% enum coverage, nested objects, and no output schema, the description provides the minimum viable context. It identifies what can be updated but omits details an agent would need for correct invocation: coordinate system, interaction enum values are in the schema but what 'update' means for them (replace vs. merge), transform semantics, and error behavior for nonexistent ids. The nested transform object and multiple shape-representation params (p1/p2 vs points) demand more guidance than provided.

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 only 17%, with only the 'id' parameter having a description ('Hit region id to update'). The other five parameters (p1, p2, points, transform, interactions) have types/schemas but no explanatory text. The description loosely references these as 'shape, transform, or interaction flags' which maps partially but doesn't explain coordinate conventions, units (pixels vs local space), how p1/p2 vs points interrelate, or whether interactions replaces or merges the existing set.

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 clearly states the verb (update) and resource (hit region) and enumerates the updatable aspects (shape, transform, interaction flags). It distinguishes from imgui_add_hit_region and imgui_remove_hit_region siblings by implying this is a modification operation. However, it doesn't explicitly name any sibling as an alternative or delineate scope boundaries beyond the three categories.

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 provides partial usage guidance by noting 'Only provided fields are updated,' which implies partial-update semantics and helps the agent know that unspecified fields are preserved. However, there's no explicit when-to-use vs. alternatives guidance, no mention of prerequisites (the hit region must exist), and no indication of when to prefer this over add/remove functions.

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