goodnotes_navigate

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

Beyond the readOnly/destructive annotations, it discloses a genuinely important lifecycle trait: a fresh viewId is returned and all previous targets expire. That invalidation rule is exactly the kind of state behavior annotations cannot express. It stops short of explaining how targets are obtained or whether prior viewIds become unusable.

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 operation list front-loaded and the critical viewId invalidation second. Nothing is wasted, though slightly denser packing of the parameter meanings would have been possible.

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 5-parameter, no-output-schema tool that mutates navigation state, the description covers the operations and the refresh contract but leaves the required viewId acquisition path and the meaning of 'targets' unexplained. An agent could not call it correctly without first discovering how to get a viewId elsewhere.

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?

With 0% schema description coverage, the description must carry parameter meaning; it maps page, zoomSteps, and panX/panY to their units and semantics ('steps', 'scroll pixels'), which is real added value. However, viewId — the only required parameter — is never explained as an input or where to obtain one, and the step/pan ranges go undocumented.

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 three concrete verbs and their resources (open a page, zoom by steps, pan by pixels), so the agent knows exactly which navigation operations are available. It is clearly distinguished from siblings like inspect, find_objects, and export, though it does not name any alternative tool.

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?

Usage is implied by the verb list, but there is no statement of when to reach for navigation versus inspection or listing, and no prerequisites or exclusions. The agent must infer that this is the way to change the viewport before other view-dependent operations.

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