get_media_captionsList caption and subtitle tracks on a recorded lecture with their languages and IDs to identify which captions to download.
List the caption (subtitle) tracks on a recorded lecture with their languages and IDs. Read-only. Captions are the closest thing to a transcript; save one with download_media_captions.
| Name | Required | Description | Default |
|---|---|---|---|
| media_id | Yes | media_id from list_media_objects |
Changes observed during successful MCP inspections.
v1.0.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false), so "Read-only" is a redundant restatement rather than added value. What does add value is the return-shape hint (language + ID per track) and the characterization of captions as transcript-like, which tells the agent what it will get and why it matters.
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 sentences: identity, safety, then the routing hint — all front-loaded with zero filler. Nothing could be cut without losing routing or return-shape information.
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?
Simple one-param listing tool with annotations carrying safety; the missing output schema is partly compensated by the description naming the returned fields. Only gaps are pagination/empty-result behavior and whether every media object has captions, which are minor here.
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?
Only one parameter and schema coverage is 100%; the schema itself documents that media_id comes from list_media_objects. The description adds no format, constraint, or sourcing detail beyond that, so the baseline 3 applies.
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 and resource — "List the caption (subtitle) tracks on a recorded lecture" — and enumerates what the result carries (languages, IDs). It is trivially distinguishable from download_media_captions (which saves) and list_media_objects (which supplies the media_id).
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 the agent to the sibling: "save one with download_media_captions," making the list-vs-download split obvious. It does not state exclusions (e.g., caption availability depends on the media object) or prerequisites beyond that, so it stops short of full when/when-not guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.