preview

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

With no annotations the description carries the full burden, and it does disclose one important trait: output is read from SOURCE MEDIA rather than the XML. However it says nothing about permissions, cost of rendering proxies, output formats, or how the read-only/mutating nature of the actions varies.

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?

Front-loads the value proposition ('See the edit without opening Final Cut Pro') and packs the action list into a single trailing sentence. Slightly dense given five actions are named, but no sentence is wasted.

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 five-way dispatcher with no output schema and no annotations, the description covers the broad purpose and one action's usage, but leaves the distinct inputs and outputs of preview_render, preview_sheet, preview_frame, and preview_timeline unspecified.

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 100% and the schema itself documents 'action' and the 'args' object including the expected_sha256 guard, so the description does not need to explain parameters. It repeats the enum values already listed in the schema, adding no meaning beyond it.

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 concrete verb and resource ('render a proxy video of the timeline, a contact sheet, a single frame...') and enumerates all five dispatched actions. It distinguishes itself from the editing siblings by being the no-FCP viewing path, though it never explicitly contrasts itself with 'view' or 'inspect'.

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?

Provides one concrete routing rule ('Run preview_check to confirm a fix actually landed'), which is genuinely useful, but gives no when-to-use guidance for the other four actions nor any guidance on when to prefer this over 'view', 'inspect', or 'scenes'.

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