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

Annotations declare non-readOnly, non-destructive, non-idempotent; the description adds the key behavior that unscheduling leaves the post as a draft rather than cancelling it, which explains why destructiveHint is false. It also adds the published-post constraint, which is not in the schema. Auth requirements and return behavior are not covered.

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 the primary action, then parameter routing, then the constraint. No filler sentences.

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?

Given four parameters, full schema coverage, and no output schema, the agent has enough to call this correctly: what it does, how to pick the mode, and when it fails. Only the conflict case (multiple mode parameters at once) is left uncovered.

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 the baseline is 3, but the description adds value beyond the schema by framing scheduledTime and useNextFreeSlot as alternative paths to the same outcome. It does not address what happens if both are supplied or if unschedule is combined with the others.

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: changes when a scheduled post publishes, or unschedules it back to draft. The two modes are spelled out clearly. It stops short of naming siblings like delete_schedule or cancel_campaign_posts, so the agent must infer that this tool does not delete.

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 routes parameter choice: 'Pass scheduledTime for a specific moment or useNextFreeSlot to take the next opening.' It also gives a real exclusion — a post that has already gone out cannot be moved. Missing an explicit pointer to delete_schedule for outright removal.

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