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

Annotations already declare destructiveHint and idempotentHint; the description adds important nuance beyond them: a pending edit is cancelled, but an Adobe transaction already running may finish. It also instructs reading the final status, which is valuable partial-completion guidance. Auth and rate-limit details are absent.

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 short sentences, purpose front-loaded, with no filler. The terse fragments ('Read its final status.') are efficient, though slightly abrupt.

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?

Covers the key things an agent needs for a destructive cancellation: prerequisite device lookup, the fact that in-flight work may complete, and the follow-up status read. The main omission is the origin or meaning of requestId, which is a required parameter.

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 coverage is only 50%. The deviceId guidance repeats the schema's own description ('from premiere_list_connections'), adding no new meaning, and the required requestId parameter has no description in the schema or the tool description. The description fails to compensate for the coverage gap.

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 and resource ('Cancel a pending Premiere edit'), and the Premiere qualifier distinguishes it from the sibling aftereffects_cancel_edit. An agent can identify the operation without opening any schema.

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?

Gives an explicit prerequisite ('First call premiere_list_connections to get the deviceId') and points to the follow-up status check. It does not explicitly state when not to cancel or name alternative siblings, but the context is clear.

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