goodnotes_arrange_object

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

Annotations already declare destructiveHint=true and openWorldHint=true, so the mutation risk is signaled structurally. The description adds a genuine behavioral instruction — verify appearance after applying, and for toggles verify the inverse command after reload — which is context annotations cannot convey. However, it never says what state is destroyed, whether the operation is reversible, or what a failed guard looks like; the phrase 'its native inverse command after reload' is opaque.

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?

It is a single compact sentence with no filler and the primary action is front-loaded before the semicolon. But the density crosses into obscurity: three separate obligations (apply, verify appearance, verify inverse for toggles) are packed into one clause whose referents ('its', 'native inverse command') are unclear.

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 destructive, three-required-parameter mutation with no output schema and 0% schema coverage, the description should clarify the operationId contract and the reload/verification semantics. It gestures at a verification workflow, which is valuable, but leaves the idempotency parameter and failure behavior undocumented — too thin for this risk profile.

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 and largely fails. It hints that 'command' originates from object_options (already visible as an 8-value enum in the schema) and alludes to a 'guarded selection' for selectionId, but 'operationId' — a required, pattern-constrained parameter — is never mentioned, so its purpose (likely idempotency/correlation) is left entirely to guesswork.

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 verb+resource is reasonably specific: it applies one of a fixed set of arrangement commands (front/back/lock/collapse/hide-author) to a selection. But 'guarded selection' is undefined jargon, and the description never states plainly that this mutates the object's stacking/visibility/lock state. It also overlaps ambiguously with siblings such as goodnotes_unlock_object, without disambiguating.

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?

It does indicate a prerequisite flow — the command must come from goodnotes_object_options — which implies when to reach for this tool. It gives no explicit exclusions, though, and an agent cannot tell whether to call this or goodnotes_unlock_object for the 'unlock' enum value.

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