Download captions

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

Goes well beyond the readOnly/openWorld annotations: it discloses the 250-quota-unit cost, the track-selection preference order, the auto-generated fallback, and the SRT output format. It stops short of explaining what happens when no caption track exists at all.

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 short clauses with zero filler; the output format and fallback behavior are front-loaded and the cost is stated plainly. Every phrase carries 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?

For a simple read-only tool with no output schema, the description covers format, cost, and selection behavior well. The notable gap is the undocumented language parameter and the absence of any statement about failure when no captions exist.

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 only 33% — channel is documented in the schema, but video_id and language are bare. The description adds no meaning for these: it does not say whether language is optional, what default is used when it is omitted, or how track preference interacts with the requested language.

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 (download), resource (caption track), target (your own video), output format (SRT), and selection behavior (prefers uploaded tracks, falls back to auto-generated). It is clearly distinguishable from sibling tools like list_captions, upload_captions, and delete_captions.

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?

Usage is implied by the name and description: use this to retrieve caption text for a video rather than to list or delete them. However, it never states a prerequisite such as listing captions first to discover available languages, nor does it name an alternative tool for those cases.

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