Fetch a transcript excerpt of a publicly-indexed saved video by URL (YouTube, Instagram Reels, or TikTok). Returns the beginning of the transcript if SavedThat has already processed that video; the full transcript is available to signed-in users in the app.
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | The video URL. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full behavioral burden. It discloses the excerpt-only behavior, the processing precondition, the public-index constraint, and the signed-in users' full-transcript limitation. This covers the most important behaviors, though it stops short of error/not-processed outcome details.
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?
Two tightly written sentences present the core action, the scope, the result, and a key limitation. No filler or redundant restating of the tool name is present.
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?
For a single-parameter tool with no output schema, the description covers what returned, under what conditions, and the full-transcript limitation. It still leaves some room for exact return-format/error details, but it is largely complete for an AI agent to select and call this tool correctly.
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?
The schema only says 'The video URL.' The description adds meaningful context by specifying the accepted source types (YouTube, Instagram Reels, TikTok) and the public-index/processing condition, which helps the agent provide a valid URL and set expectations.
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 states a specific action ('Fetch a transcript excerpt'), a clear resource ('publicly-indexed saved video by URL'), and supported sources. It also clarifies the partial vs. full-transcript distinction, making the tool's scope and purpose unambiguous relative to siblings.
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?
The description makes clear this tool is for publicly-indexed videos and returns only an excerpt if processing has already happened. It also points to the in-app alternative for full transcripts, although it could be more explicit about when not to invoke it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
The two tools are entirely distinct: one provides product overview information, the other retrieves a video transcript. There is no overlap in purpose, input, or output, so an agent can easily select the right tool.
Both tools follow a consistent `get_` prefix paired with a clear object noun (`product_info`, `public_transcript`). The naming pattern is uniform and predictable.
With only 2 tools, the server feels minimal and thin. Each tool is useful and covers a distinct need, but the overall surface is borderline for a product-specific server.
The server only covers product information and a partial public transcript lookup. It lacks user-specific operations such as saving videos, listing saved items, accessing full transcripts, or managing account data, so significant portions of the domain are absent.
