Premiere full API surface

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the description's 'risk-gated' adds minimal new context. It does not disclose what operations are destructive, whether approvals are required (despite approvalId in schema), or what side effects may occur. The description adds a vague behavioral hint but fails to provide meaningful transparency beyond annotations.

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?

The description is a single sentence, but brevity without substance is under-specification, not conciseness. It fails to front-load any actionable information and uses jargon ('UXP', 'DOM/QE', 'semantic UI fallback') without explanation. The structure offers no hierarchy or key details first.

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 tool with 6 parameters, nested objects, and no output schema, the description is severely incomplete. It does not explain the approval workflow (despite approvalId and operationId), what operations can be invoked, what search results look like, or how the risk-gating works. An agent cannot safely or correctly call this tool based on the description alone.

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 0%, so the description must carry the burden of explaining parameters. It says nothing about actionId, args, target, approvalId, operationId, or expectedRevision. The agent is left with zero semantic guidance for filling the required actionId or optional fields, making parameter usage entirely 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 description uses a specific verb pair ('Search or invoke') and names a resource category ('official UXP, safe legacy DOM/QE capabilities, and semantic UI fallback'), which distinguishes it somewhat from the sibling tools that target specific domains. However, it remains vague about what 'search' and 'invoke' actually produce or accept, and it does not explicitly differentiate itself beyond being a generic 'one surface.'

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?

The description gives no guidance on when to use this tool versus the siblings. It mentions 'one risk-gated surface' but does not explain when that surface is appropriate, when to prefer it over premiere_project or premiere_timeline, or what 'risk-gated' entails. There is no mention of alternatives or exclusions.

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