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

Annotations already declare readOnlyHint/idempotentHint/destructiveHint, but the description adds real behavioral context beyond them: the exact nature of the payload (the same creator_info a human sees), the human-in-the-loop posting constraint, one-post-at-a-time, and the audit caveat. It does not cover auth/permission requirements or failure behavior, and the 'F6015/S3' code adds traceability but little agent-actionable meaning.

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 short sentences, front-loaded with 'DRAFT ONLY' so the most decision-relevant fact lands first. The posting prohibition is restated twice, which is mild redundancy but defensible given the risk of the agent trying to post.

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?

There is no output schema, and the description does compensate by enumerating the returned creator_info fields, which is genuinely useful. However, for a tool whose two inputs are completely undocumented, the definition leaves the calling mechanics underspecified even though the safety story is complete.

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 0% and the description says nothing about job_id or clip_idx, so an agent gets no signal on what to pass or whether both are optional (required count is 0). The only hint is the vague 'per-post' framing; the burden of explaining the two parameters is entirely unmet.

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 concrete verb and resource: it returns creator_info (nickname, privacy options, interaction/duration limits) for a per-post TikTok draft. It also preempts the obvious confusion by declaring 'NEVER posts -- there is no tool that does', which separates it from every sibling in the catalog.

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?

The 'when-not' case is explicit and forceful: this is not for posting, and posting requires a human click on the dashboard. What's missing is a positive routing cue naming the sibling that handles the adjacent step (e.g., clipwright_schedule or clipwright_create_clips) when an agent needs something other than creator metadata.

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