goodnotes_review_study_revision

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

Beyond the annotations (readOnlyHint=false, destructiveness not claimed), the description adds real behavioral claims: it preserves uncertain receipts, never replays mutations, and flags missing checkpoints for individual inspection. That is useful context, but the vocabulary ("receipts", "checkpoints") is never grounded, and it is silent on side effects even though readOnlyHint=false implies the tool may alter state.

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?

Three short sentences with no filler, but the front-loaded sentence buries the plain purpose under abstractions ("complete matching evidence") and the ordering puts guarantees ahead of what the tool produces. Compact but not clear.

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 single-parameter inspection tool with no output schema and non-read-only annotations, the description should at minimum say what the inspection yields and what state it may change. Instead it offers opaque guarantees, leaving the agent unable to judge return shape, failure modes, or side effects.

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?

There is exactly one parameter, revisionId, with 0% schema description coverage, so the description must carry the burden. It only obliquely implies the id refers to an interrupted revision; it says nothing about UUID format expectations, what happens with a non-interrupted or unknown id, or how the id relates to the checkpoints mentioned.

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?

"Independently inspect an interrupted revision" does state a verb and object, and "interrupted revision" hints at how this differs from the plan/prepare/run/status siblings. But "complete matching evidence" and "unchanged visible surroundings" are undefined jargon, so an agent cannot predict what the tool actually returns or how it differs from goodnotes_study_revision_status.

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?

There is no explicit statement of when to use this instead of the many other revision tools (plan, prepare, run, status, review_study_board/collection). The line "Missing checkpoints require individual inspection" implies a precondition but never says what to do instead when that condition holds, nor does it name an alternative.

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