List (and read) a video’s caption tracks

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

The description adds behavior beyond the annotations by explaining the concept of a caption track versus burned-in captions, noting that auto-generated tracks are 'read-only and cannot be edited or deleted,' and stating 'Read-only, 0 credits.' Annotations already declare readOnlyHint: true and destructiveHint: false, so the description enriches but does not contradict them. It stops short of covering response format or rate limits.

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 four sentences long, each adding value: the primary action, the conceptual distinction, the read-only caveat, and a practical use case. It is front-loaded with the core action and flows logically, though slightly verbose for a simple list tool.

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?

Despite lacking an output schema, the description hints at the list structure ('Each row says whether YouTube generated it automatically (isAutoGenerated, trackKind ASR)') and covers prerequisites, constraints, and use cases. It is fairly complete for an agent to decide when and how to call it, though it does not describe pagination or return formats.

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 parameters are already documented (e.g., format with enum and default, download as captionId or language code). The description reinforces the download behavior and mentions the read-only nature of auto-generated tracks, but it does not add substantially new parameter meaning beyond the schema. Baseline of 3 is appropriate given high coverage.

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 clearly states the tool's actions: 'List the caption/subtitle tracks on one of the connected channel’s videos, and optionally DOWNLOAD one as text.' It specifies the verb (list/download), the resource (caption tracks on a video), and distinguishes caption tracks from burned-in captions, which also separates it from sibling management tools like manage_youtube_caption.

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 provides a concrete use case ('Downloading is also the fastest way to get an existing video’s full script back for repurposing') and a prerequisite ('Needs a connected YouTube channel'). It implies read-only usage via the 'read-only' statement, which steers away from editing, but it does not explicitly name alternatives like manage_youtube_caption or list_youtube_comments.

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