youtube_clean_playlist_preview

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

Annotations already declare readOnlyHint=true, and the description reinforces rather than contradicts that with 'without changing anything', which is meaningful emphasis on a mutation-adjacent workflow. It additionally discloses return content that no output schema covers: the exact removal set, the reasons, and the plan_token needed downstream. No annotation contradiction.

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 sentences, front-loaded with the scope guarantee ('without changing anything'), followed by the return content and then the workflow instruction. Every clause earns its place and nothing is repeated from the schema.

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 preview tool with no output schema, the description covers the return shape, the safety guarantee, and the handoff to the apply tool, which is what an agent needs to call it correctly. Minor gaps remain: no mention of what happens when nothing matches the remove criteria, or any limit on how large a playlist can be previewed.

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%, so playlist_id, remove, and watched_threshold are already fully documented, including the enum meanings and the default of 90 percent. The description adds nothing beyond the schema for any parameter, so baseline 3 applies; this is a minor missed opportunity to note that watched_threshold is only relevant when 'watched' is in remove.

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 gives a specific verb and resource ('Preview a playlist clean-up') and immediately states the key differentiator from its sibling: it changes nothing, whereas youtube_clean_playlist_apply does. It also names the concrete return content (the videos that would be removed, the reasons, and a plan_token), so an agent can distinguish it from every other playlist tool without opening a 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?

It explicitly names the alternative tool (youtube_clean_playlist_apply), states the ordering constraint ('Show the list to the user before applying'), and links the two via plan_token. That is a complete when-to-use-this and when-to-use-the-other instruction rather than an inference the agent has to make.

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