Run the posting refill

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

Annotations declare destructiveHint=true, readOnlyHint=false and idempotentHint=false, and the description adds substantial context beyond them: dry-by-default behavior, exactly what a preview returns, that nothing is queued or spent, the human-approval requirement before real posting, and the caption-screening rule that can shorten the plan with the reason in notes.

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 constraint — dry by default and preview before real posting — is front-loaded and capitalized for emphasis. Every sentence carries distinct information (default behavior, opt-in, safety requirement, screening side effect); none is padding.

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, so the description compensates by enumerating what the preview contains (caption, creative, channels, per-channel visibility) and explaining why a plan may return shorter than the cadence. Complete for a two-parameter, zero-required tool with a destructive side effect.

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 100%, so baseline is 3, but the description goes further by explaining the interaction the schema does not: that force combined with dryRun:false still respects a stored dryRun, and why force exists (showing what a disabled refill would do). That interaction semantics is genuine added value.

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 and resource ('Run the refill NOW instead of waiting for its daily turn') with clear scope and timing semantics. It is easily distinguishable from get_post_refill and set_post_refill, which configure or inspect the refill rather than execute it.

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?

Gives explicit when-to-use ('run NOW instead of waiting'), when-not and how ('SHOW THE PREVIEW TO THE USER BEFORE EVER PASSING dryRun:false; these go onto real public accounts'), and the alternative path (default preview vs. dryRun:false to queue). 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.