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

Annotations only give the generic mutation profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false); the description goes well beyond them by disclosing the required `write` scope, that a new draft is created in the card's brand with labels format:motion-ad and source:template, that nothing is posted, that the source card is unchanged, that it is free, and that the result is asynchronous via jobId.

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?

It is dense but front-loaded, with the scope tag and write classification first, then the output structure, then side effects and follow-up. The trailing wrapped-endpoint note is the weakest line, though it usefully identifies the underlying API surface.

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 8 parameters, no output schema, and several mutation side effects, the description covers everything an agent needs: inputs' meaning, defaults, what is created, what is left untouched, costs, and how to retrieve the result via get_job_status. No significant gap remains.

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 63%, and the description compensates on several keys: contentId is defined as the Library image card, aspect defaults to 9:16, the CTA URL's host is what appears on the end card, and text inputs are used verbatim rather than rewritten. textColor and brandColor gain no detail in the description beyond the schema's #RRGGBB notes, keeping it below a 5.

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 opens with a precise verb+resource ("Turns one Library image (the card) into a 6-15 s motion ad") and enumerates the produced structure: hook push-in, up to 3 body beats, CTA end card. This is clearly distinguishable from sibling render/edit tools like combine_clips, apply_frame, or create_frame.

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?

It tells the agent the preconditions and outcomes that drive selection: writes with the `write` scope, saves a new draft rather than posting, leaves the card unchanged, and is free. It also routes the follow-up step explicitly ("Returns a jobId: poll get_job_status"). It stops short of naming when to pick this over other creation paths, 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.