pr_applyEditPlan

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

Adds real behavior beyond the annotations: steps execute in declared order, execution halts at the first error unless stopOnError:false, and non-Premiere native steps are permitted. It omits what matters most for a mutation batch — that a mid-plan failure leaves earlier edits applied with no rollback, and that plans may embed destructive steps (e.g. pr_removeClips, ae_deleteLayer) even though destructiveHint is false.

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 sentences plus a parenthetical, with the core action and ordering guarantee front-loaded and the example placed where it is needed. No filler and nothing redundant with the schema.

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, the description should say what a plan returns (per-step results? final state? the failing step?) and does not. Ordering and abort semantics are covered, but atomicity/partial-application behavior — critical for an arbitrary-tool dispatcher — is left unstated.

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 must carry the burden — and it does for both parameters. The inline example {tool:"pr_addMarkers", input:{...}} shows the required nested keys and stopOnError is defined by negation ('unless stopOnError:false'), though it never states the default explicitly or whether input is optional.

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 action and resource: run many pr_* steps in one call, in order, with a concrete inline example of the step shape. The parenthetical that ae_/ps_/ai_/xapp_ steps can be mixed in broadens scope usefully but also blurs the pr_ prefix, and the description never distinguishes itself from the sibling adobe_batch, which appears to serve an overlapping dispatch role.

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 context is implied by 'run many pr_* steps in ONE call' — an agent can infer this is for batching rather than single operations. However, there is no explicit guidance on when to call the underlying tools directly instead, and no comparison against the sibling adobe_batch or adobe_catalog_call that also batch work.

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