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

Annotations already cover the safety profile (readOnly, idempotent, openWorld, non-destructive), but the description adds real behavioral context beyond them: return format, best-first ordering with scores, and the key trait that it 'never picks' because multiple candidates may mean multiple objects or a wrong match. This ambiguity disclosure is exactly what an agent needs and is not captured by annotations.

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 with the purpose, then the return shape, then the workflow caveat — three dense, purposeful sentences with no filler. Slightly compressed but every clause earns its place.

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 carries the burden of explaining returns and does so (candidate boxes [x1,y1,x2,y2] in document pixels, best first, with scores). The downstream workflow is also covered, leaving only minor gaps like the meaning of the `max` cap.

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 80%, so the schema already documents word, image, layer, and layer_id. The description adds no syntax or format detail for parameters beyond the implied 'by name' mapping to `word`, so the baseline of 3 applies.

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 specific verb+resource ('find things by name') and immediately distinguishes itself from select_with_ai by noting it 'never picks'. The agent can tell this is a candidate-generation tool, not a selection tool, without opening any schema.

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?

Explicitly routes the workflow: check the returned boxes ('preview with a region') before passing one to 'select_with_ai target=object'. It names the downstream alternative and the condition that selects it, so the agent knows both when to call this and what to do next.

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