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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, so the safety profile is covered. The description adds genuinely non-structured context: no AI/LLM cost, a 20-video cap, and per-video status isolation with bundled metadata, which tells the agent a partial failure won't abort the whole batch.

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 action and scope, and the cap is stated up front. Slight redundancy: 'free, no AI' and 'Free, no payment required' restate the same point in two places.

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?

An output schema exists, so return-value detail is unnecessary. The description covers input format, batching limit, and failure isolation. The only gap is explicit routing against the single-transcript siblings.

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 baseline is 3, but the description adds cross-parameter meaning: the two inputs can be combined ('and/or') and the batch is capped at 20. That interaction is not spelled out by the schema alone.

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 ('Fetch transcripts + metadata'), plus the distinguishing scope ('for many YouTube videos at once'). This separates it cleanly from siblings transcript_text and transcript_markdown, which imply single-video retrieval.

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?

Gives input-shape guidance ('Comma-separated video URLs/IDs and/or a playlist URL') and a hard cap, which implies when it is appropriate, but never explicitly names the single-video alternatives or states when to prefer them. Usage is inferable rather than stated.

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