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

With no annotations the description carries the full burden, and it discloses what is returned as well as access scope ('anyone's shared collection, or your own private one') and the special 'favourites' input. It omits auth/permission specifics for private collections and any rate-limit or pagination notes.

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-loaded with the core output statement, then input forms, then downstream usage. Sentences are dense but each earns its place; the chained references to plan_video/get_blueprint add mild length but useful routing.

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?

No output schema, so the description's enumeration of card contents is valuable and largely compensates. Combined with the id-format and downstream guidance, an agent has enough to call it correctly, though permission behavior for private collections is left implicit.

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%, so the schema already documents id formats and the limit default. The description reinforces the id variants (collection id, refs.video/c/… link, 'favourites') but adds no syntax beyond the schema and never mentions limit.

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+resource ('Every film in a Refs collection as search cards') and enumerates the returned fields (REF id, link, length, aspect, metrics, why it works). This clearly separates it from list_collections (which lists collections) and get_blueprint (one film in depth).

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?

Explicitly routes downstream: use returned cards with plan_video(brief, reference_ids), up to 5, or get_blueprint for a single film. It doesn't name list_collections as the way to discover ids or state exclusions, so it falls just short of a full when/when-not treatment.

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