Plan Multicam Angle Switches

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context beyond annotations: it is 'Local-only and deterministic; never changes Premiere.' This tells the agent the tool is a pure computation/planning tool with no side effects on the project, which is exactly the kind of context that helps an agent reason about invoking it. It also discloses that it produces a plan (not applying edits), which is a key behavioral trait. It doesn't describe failure modes or edge cases, but the annotations plus the explicit 'never changes Premiere' cover the most important behavioral aspects.

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, dense sentence that front-loads the core purpose and then lists the key outputs and constraints. Every clause earns its place: the input sources, the output artifacts, and the safety guarantee. It is long but information-dense, and the structure (purpose → inputs → outputs → constraints) is logical and scannable. No wasted words.

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?

Given the tool's complexity (12 params, 2 required, nested camera/speaker objects) and the presence of a rich output schema, the description is largely complete. It tells the agent what the tool produces, what it consumes, and that it is side-effect-free. The only minor gap is that it doesn't explicitly state the relationship to sibling planning tools (e.g., plan_speaker_checkerboard, plan_active_speaker_reframe) or how the output plan would be consumed downstream (e.g., by apply_edit_plan). But the output schema likely covers the return structure, and the description covers the essential invocation context.

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 100%, so the schema already documents all 12 parameters thoroughly. The description adds a high-level summary of what the parameters collectively do (minimum holds, crosstalk cover shots, lead-in cuts, periodic cutaways) but does not add per-parameter meaning beyond the schema. Baseline 3 is appropriate because the schema carries the heavy lifting and the description provides a useful conceptual frame without duplicating every detail.

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 states a specific verb ('Plan'), a specific resource ('active-speaker camera switching for stacked, synced camera tracks'), and enumerates the concrete outputs (angle cut list, razor times, per-camera enable/disable ranges, markers). It also distinguishes itself from siblings by naming its inputs (speaker segments, camera-to-speaker map) and its deterministic, local-only nature. This is a clear, specific purpose that an agent can act on.

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 implies when to use it: when you have speaker segments and a camera-to-speaker map and want to plan multicam angle switches. It also states what it does NOT do ('never changes Premiere'), which helps an agent avoid using it for actual timeline edits. However, it does not explicitly name alternative tools or state when NOT to use it (e.g., use apply_edit_plan to apply the plan, or plan_speaker_checkerboard for a different kind of plan). The context is clear but exclusions are not explicit.

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