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

Annotations declare destructive=true and openWorld=true, but the description goes well beyond them: it discloses that posts are externally visible, that one monthly video is consumed per variation, that the same variation never hits two accounts or posts twice, that surplus variations spill to next days, that carousels never go to YouTube, and that originals precede translations. This is rich behavioral context an agent cannot get from the annotations.

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 purpose is front-loaded and every sentence carries operational detail, but the single dense paragraph packs scheduling rules, language ordering, and platform constraints into a run-on that is hard to scan. It is information-dense rather than padded, so it largely earns its length.

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 complex 9-parameter mutation with no output schema, the description is nearly complete: it covers the scheduling algorithm, dedup/idempotency behavior, language ordering, platform constraints, cost, and even notes per-entry results. The only minor gap is the absence of expected error/idempotency-conflict behavior, which an agent would want for a destructive 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?

Schema coverage is 78%, putting the baseline at 3, but the description adds genuine meaning: the plan vs server-planned mutual exclusion, that languages selects which variations to hand out (with 'original' semantics), and the per-account-per-day counting rule tied to timeZone. It stops short of explaining jitterMinutes or idempotencyKey semantics beyond what the schema already notes.

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 specific verb+resource with clear scope: it spreads DIFFERENT variations of one cloning job across the brand's social accounts at staggered times. This is distinguishable from siblings like add_clone_variations, save_clone_variation_to_library, and publish_content without opening any 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?

Explicitly lays out the two invocation modes (server-planned via socialAccountIds+startAt+spacingMinutes vs explicit plan entries), names the sibling tools that supply inputs (get_clone_job for pieceIds, list_publish_destinations for account ids), and states prerequisites (variations must be rendered and not already scheduled). It also notes that re-calling only fills gaps, which prevents accidental duplicate scheduling.

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