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

Annotations supply readOnlyHint=true and openWorldHint=true, so the safety profile is covered; the description aligns with them by framing the output as a 'draft' rather than a save. It adds real behavioral context beyond annotations: drafts imitate the user's own voice and structure learned from their prior descriptions. It does not state whether the draft is persisted back to YouTube, which is the only notable gap.

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 action, then usage triggers, then parameter routing, then the sibling exclusion — a logical order with no filler. It runs slightly long with 'or the text/notes/blurb under a video,' which is useful disambiguation rather than padding, but the last two clauses could be tightened.

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?

No output schema exists, so the description carries the burden of explaining the return, which it does not do (e.g., whether a draft is saved or just returned, and in what form). With five optional params and no required ones, an agent also lacks guidance on which combinations are valid or what happens with `topic` vs `idea`. Adequate for calling, incomplete for predicting results.

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 60% and the description meaningfully explains three of five params (`video`, `idea`, `title`), including when each applies. However, `topic` and `video_title` are undocumented in both the schema and the description, leaving ambiguity about how `topic` differs from `idea` and when `video_title` applies. Helpful but incomplete compensation.

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?

Specific verb+resource ('Draft a YouTube video DESCRIPTION') plus scope ('for the signed-in user, in their own voice'). It explicitly excludes siblings' territory: 'for titles and thumbnails use package_video.' An agent can distinguish it from package_video, draft_script, and suggest_ideas 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?

Explicit trigger conditions ('when the user asks to write, draft, rewrite, or improve a video description... or the text/notes/blurb under a video') and routing logic: pass `video` for an existing upload, `idea` for a new one, `title` when agreed. It also names the alternative tool for the adjacent job. Nothing is left to inference.

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