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

Annotations already declare read-only, open-world, non-idempotent, non-destructive, so the description is free to add the traits that matter operationally: the transcript cap of 5 and 12,000-character truncation, the 'no_transcript' outcome for caption-less videos (most Instagram reels), and the 1-credit-per-transcript cost with failures free. That is real cost and failure-mode disclosure not present in structured fields.

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 sentences, front-loaded with purpose and platform scope, then alternatives, then the opt-in transcript behavior. Every sentence carries distinct information; nothing is padding.

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 an 8-parameter, multi-platform search tool with an output schema, the description covers the platform default, the YouTube-only filter cluster, the sibling alternative, the cost model and the failure mode. Return shape is handled by the output schema, so nothing an agent needs before calling is missing.

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% and the enum semantics (duration buckets, upload_date windows, sort, captions) are already fully documented there, so baseline is 3. The description adds only light framing — that these filters are YouTube-only and that 'transcripts' returns content 'in the same call' — which is useful but largely restates the schema.

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 ('Search for videos matching a query') and immediately scopes it across YouTube (default), TikTok and Instagram. It also names the sibling that does something adjacent ('search_channels finds channels or playlists instead'), so the agent can route without opening either schema.

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?

Explicit routing is given: use search_channels for channels/playlists, use this when you want video rows, and set 'transcripts' when you need what the videos say rather than only titles. The follow-on relationship to get_transcript ('URLs that get_transcript accepts directly') is spelled out, which is the key when-to-use chain.

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