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

With no annotations, the description carries the full burden and does disclose the mutation's side effects: cancelling linked publishing history 'when still cancellable' (conditional behavior made explicit) and clearing publishing_history_id and scheduled_at. Not covered: required permissions, idempotency/repeat-call behavior, or what occurs when the history is already published and no longer cancellable.

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?

Two dense sentences: the action and its side effects come first, the alternative-preference note last. No filler, and the field-clearing detail is parenthetically front-loaded.

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 mutation tool with no annotations and no output schema, the description explains what changes and under what condition, which is the essential information. Remaining gaps — auth requirements and behavior for rows that cannot be unscheduled — are real but secondary.

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 100% for the single optional notification_message parameter, so the schema already documents it fully. The description adds nothing about the parameter, which is acceptable at full coverage but leaves the baseline.

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 ('Unschedule') and resource ('one calendar row') and immediately enumerates the mechanics: cancelling linked publishing history and resetting the row to draft. It contrasts with patching scheduled_at alone, but never names the closely-related siblings (delete_calendar_row, cancel_publishing_history, update_calendar_row), so an agent must still infer the boundary.

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 clause 'Prefer this over PATCH scheduled_at alone' gives an explicit preference and implied alternative path. It does not cover exclusions — when to call cancel_publishing_history or delete_calendar_row instead, or what happens if the row was never scheduled.

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