goodnotes_plan_study_revision

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

Annotations declare readOnlyHint=false, destructiveHint=false, openWorldHint=true, so the description does not need to re-establish safety, and it instead adds substantive context: untouched objects are retained, source pages and intermediate geometry are validated, a preview is saved, the plan is frozen, and unmanaged personal notes are excluded from the preview. It also flags that sourceExportId text/page change reporting still requires diagram review. It does not explain what happens to the frozen plan afterward or how previews are retrieved.

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?

Four dense sentences, front-loaded with the primary operation and followed by retention, preview/freeze behavior, and the sourceExportId caveat. Every sentence carries information, though terms like 'intermediate geometry' and 'bounded object moves' are terse enough to be ambiguous to a first-time caller.

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 complex mutating planner with a large nested input schema, no output schema, and zero schema descriptions, the definition covers intent, safety, and one optional parameter's caveat. It omits what the tool returns (e.g., a plan or revision identifier), how the frozen plan is consumed downstream, and meaning for most nested fields, leaving real gaps for correct invocation.

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 on a deeply nested schema, the description has to carry parameter meaning, and it partially does: it maps to the three change categories (updates, moves, new sections/appendY), explains sourceExportId's role and its limitation, and 'bounded' hints at the coordinate clamps. However, nested fields such as layout flow, columns, figures crop/span, card roles, and sections remain unexplained.

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 states a specific verb and resource set: plan card updates, bounded object moves, and new sections below an existing managed board. It also names the key behavioral artifacts (preview saved, plan frozen). It does not explicitly contrast itself with goodnotes_plan_study_board or goodnotes_run_study_revision, so sibling differentiation is left implicit.

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 through the workflow language ('saves a preview and freezes the plan'), which suggests a planning stage preceding review/run, but there is no explicit when-to-use guidance, no prerequisites, and no named alternative for the non-revision planning case. An agent must infer the stage from the tool name and sibling family.

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