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

Annotations already declare readOnly/idempotent/non-destructive, and the description goes well beyond them: per-account rate limit, minimum poll interval, the semantic gap between transfer completion and encodability, playlist refusal behavior, fileId persistence after completion, and the fact that `files` reflects live state and can shrink. None of this is derivable from the 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?

Three short paragraphs, each with a distinct job: return fields first, then the done-vs-usable caveat and rate limit, then the YouTube playlist/folder special case. No sentence is decorative, and the most important output field names are front-loaded.

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?

There is no output schema, so the description carries the full burden of describing return values, and it does: status, progress percentage, pollAfterSeconds, usable, nextStep, isFolder, and files. It also closes the obvious follow-up gap by noting that `files` names videos without ids and pointing at livereacting_list_media.

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?

There is only one parameter and schema coverage is 100%, so the schema already documents the fileId pattern and origin. The description nonetheless adds lifecycle meaning the schema lacks: the fileId remains valid and pollable after the import finishes, which tells the agent it can re-invoke rather than cache a one-shot token.

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 specific verb+resource ('Check how far an import ... has got') and names the exact sibling tools that produce the fileId (livereacting_import_media, livereacting_import_from_url). It also enumerates what the call returns (status, progress percentage, pollAfterSeconds), so an agent can distinguish it from livereacting_get_encode_status without opening a schema.

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 states the trigger condition (after an import started by one of the two import tools), the polling cadence (no more often than once every 10 seconds), the reason (150 req/min account budget), and where to go next via `nextStep` when `usable` is false. The distinction between `done` and `usable` is explicitly flagged as a usage trap, which is exactly the kind of when/when-not guidance this dimension rewards.

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