goodnotes_verify_copied_object

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

Annotations declare readOnlyHint=false, destructiveHint=false, openWorldHint=true, and the description adds real semantics beyond them: it reacquires the page across zoom changes and runs type-specific content checks or appearance comparison against captured source. The explicit 'never pastes again or rewrites the old receipt' clarifies a non-destructive, idempotent verification posture, consistent with readOnlyHint=false (the page/zoom state is touched, content is not). It does not disclose what happens on a failed verification.

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?

A single dense sentence with zero filler, front-loading the action and scope before the behavioral clauses. It is jargon-heavy ('captured source appearance', 'old receipt') and packs three distinct behaviors into one breath, slightly reducing scannability.

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 and an entirely undocumented parameter, the description should explain what a verification yields (pass/fail, mismatch detail) and where the checkpoint identifier originates. It covers the 'what it does and does not do' side well but leaves the invocation-side essentials implicit.

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?

The single parameter, operationId, has 0% schema description coverage with no pattern or format explanation, and the description never mentions it. 'Its saved local checkpoint' hints that the identifier refers to a prior checkpoint, but an agent still cannot tell where operationId comes from, whether it is the copy or paste receipt, or what the required format means.

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 (verify) and a precisely scoped resource: an existing paste of native text/sticky/image or lasso selection, checked against its saved local checkpoint. The scope word 'copied' plus 'paste from checkpoint' distinguishes it from siblings like verify_moved_object and verify_restore without needing to name them.

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?

Clearly establishes the context: this runs after a paste already happened, against a saved checkpoint. It also carries an explicit when-not ('never pastes again or rewrites the old receipt'), which steers an agent away from treating it as a paste action. It stops short of naming an alternative tool or stating the prerequisite that a checkpoint/operationId must already exist.

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