click

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

Annotations already declare readOnlyHint=true, openWorldHint=false, idempotentHint=false, so the safety profile is covered. The description adds genuinely new behavior: the response reports full object identity and also enumerates nearby candidates, plus the follow-up path via `select`. It does not mention that the pick replaces the current selection unless `add` is set, which is the main reason idempotentHint 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?

Two tight sentences: the action and return content come first, the fallback path second. Every clause carries information an agent needs, and nothing is padded.

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?

With no output schema, the description takes on the job of describing return values and does so explicitly. The remaining gap is the empty-pick case (what is reported when nothing is under the point) and the selection-replacement side effect, both of which an agent would want before calling.

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 60%: `add`, `coords`, and `tolerance_px` are documented in the schema, while `x`/`y` are bare. The description's 'under the point' implies the coordinates but does not clarify the pixel-vs-world interpretation or the tolerance behavior, so it adds little beyond the structured fields. Baseline 3 is appropriate.

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?

States a concrete verb and resource ('click on the drawing: select the object under the point') and enumerates the reported attributes (type, layer, coordinates, text, block attributes, size), so the agent knows exactly what it gets back. It differentiates itself from the sibling `select` (handle-based selection) but leaves overlap with `inspect`/`find` unaddressed.

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?

Gives a clear operational context: the pick returns nearby alternatives and, if the wrong one was hit, the agent should call `select(handles=[...])`. That is an explicit alternative plus the condition that selects it. It does not say when to prefer this over point-free siblings like `inspect` or `find`.

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