goodnotes_find_objects

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

Annotations already cover the safety profile (readOnly, non-destructive, open-world), so the description's added value is its disclosure of return shape ("compact candidates with coordinates/confidence", "no screenshot tokens") and its key limitation (visible-only, requires rescan after panning). That is real behavioral context beyond the structured fields, though it stops short of noting cost or rate characteristics of repeated scans.

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 with the primary action front-loaded and the limitation trailing as a caveat. Every clause carries information; the only mild oddity is the negative framing of "no screenshot tokens," which is useful but slightly cryptic out of context.

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 does partially compensate by sketching the return payload (candidates with coordinates and confidence). But for a three-parameter OCR search whose schema is entirely undocumented, an agent is still guessing about query semantics and confidence thresholding, which is a meaningful gap for this complexity level.

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%, so the description carries the full burden for three parameters and does not meet it. It never explains what "query" matches (substring, fuzzy, empty-means-all), what viewId identifies, or that minConfidence is a 0-100 threshold with a default of 40 — confidence is only alluded to obliquely via the return value.

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 uses a specific verb+resource pair ("Find visible text locations on a board") and qualifies it with the mechanism ("local OCR") and scope ("visible"). That is precise enough to separate it from OCR-adjacent siblings like convert_handwriting, but it never names an alternative tool to differentiate itself 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?

The second sentence gives an actionable constraint: off-screen content requires pan/zoom plus a rescan, which implies when this tool is and isn't sufficient. However, there is no explicit routing guidance to a sibling (e.g., a full-board or exhaustive search tool), so the agent must infer the alternative.

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