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

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true, openWorldHint=false, and the description stays consistent with them by stating it 'opens nothing by itself'. Beyond that it discloses the meaningful behavioral trait an agent could not infer from annotations — that the return payload is step-by-step instructions rather than draft data. The trailing note 'CapCut's official API: Partly' is too cryptic to count as real disclosure.

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?

The critical fact — that this tool returns a guide and performs no action — is buried mid-sentence rather than front-loaded, and could easily be missed. The fragment 'CapCut's official API: Partly.' is dangling and adds ambiguity rather than value. The workflow handoff sentence does earn its place.

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?

With no parameters, no output schema, and safety fully covered by annotations, the remaining burden is explaining what comes back — and the description does that ('step by step (screens, buttons, fields)') plus what to do next. It lacks any note on failure cases or what the guide looks like when the user is not signed in, but that is a minor gap for a zero-argument instructional tool.

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 tool takes zero parameters, so there is no parameter semantics to explain and the baseline of 4 applies. The description correctly emphasizes that the only variable is the user's own CapCut account context.

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 name says 'List drafts', but the description reveals the tool does not list anything itself — it 'Returns how to do it in CapCut step by step (screens, buttons, fields)'. That is a genuine clarification, but the opening sentence 'List drafts in the user's own CapCut account from ChatGPT, Claude or any AI agent' is ambiguous about whether drafts come from those agents or are merely accessed through them. An agent must read past the name to learn this is a guidance tool, not a data-returning one.

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 states the follow-up path explicitly: the returned guide is then executed with the cotlet_browser_* tools in the user's CapCut Cloud Browser, which names the alternative tool family in siblings. It also scopes the account to 'the user's own', implying no cross-user access. It stops short of saying when NOT to call this versus e.g. cotlet_app_guide or cotlet_browser_find directly.

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