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

Goes well beyond annotations: it discloses that scheduling does not publish immediately, that SuperPost publishes at each selected future time, and that the server rechecks revisions, hashes, provider targets, media, channel mapping, and time before applying the batch. It also spells out the authorization requirement and the narrow condition for approveExactContent. This is consistent with the supplied hints (not read-only, idempotent, non-destructive, open-world).

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 prerequisites, then behavioral guarantees. Four sentences and none is filler; the authorization caveat and the recheck sentence are both load-bearing for correct invocation.

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?

A complex, irreversible-feeling, open-world mutation with an output schema; the description covers authorization, idempotency, confirmation, deferred publish timing, and server-side validation. What it omits are batch limits (maxItems 32), how to handle scheduling failures, and any mention of the item-level fields, though the output schema covers return values.

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 0%, so the description must carry the load, and it does for the top-level parameters: idempotencyKey must match the preview, confirmation must be the exact constant, and approveExactContent is scoped to that exact item and only when the user explicitly authorized the content. Gaps remain on 'items' sub-fields (targetKey, variantId, localDateTime format, dstDisambiguation), and it calls the parameter 'previewHash' where the schema says 'expectedPreviewHash.'

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?

Opens with a specific verb and resource: 'Applies a previously returned future-schedule preview by creating scheduled slots.' It also distinguishes itself from the preview step by framing itself as the application/commit half of that pair, so an agent knows this is the executing tool, not the preview tool.

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?

States hard preconditions clearly: the exact previewHash, the same idempotencyKey used for that preview, and confirmation=CONFIRM_FUTURE_SCHEDULING, plus the point that OAuth permission alone does not authorize a particular schedule. What's missing is an explicit naming of the pairing sibling (preview_schedule_posts) as the required preceding step, though it's strongly implied by 'previously returned future-schedule preview.'

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