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

Annotations only flag destructive/openWorld/non-idempotent; the description goes well beyond them by disclosing the required `content:write` scope and the exact two-phase dry-run contract, including that the first call changes nothing and returns a summary plus confirm_token. That is precisely the behavioral context an agent needs before invoking a destructive tool, and it is consistent with destructiveHint=true.

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?

Roughly sixty words, front-loaded with the action and the permission requirement, then the call sequence in order. Every sentence carries information the agent needs (scope, two calls, non-mutating first call, human confirmation gate) with no filler.

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?

With no output schema, the description responsibly explains what the first call returns, which is the key missing piece. It leaves out what happens to the event's existing content or public link after unpublishing, and whether republishing restores it, but the tool is simple enough (2 params, one required) that this is a minor gap.

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?

The schema already documents confirm_token, but the description adds real meaning: the token comes from the first call's answer and must be paired with 'the same arguments'. It also explains that the first call validates 'as the change would' and refuses unknown fields by name, which tells the agent how arguments are evaluated. The `id` parameter is undocumented in both places, matching the 50% schema coverage.

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?

The description names a specific state transition on a specific resource: a live event is moved 'back to draft', which is clearly a verb+resource statement rather than a restatement of the name. It does not explicitly distinguish this from the adjacent state-changing siblings (archive_live_event, cancel_live_event, update_live_event, delete_live_event), so an agent must infer the difference from the 'draft' wording alone.

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?

Usage is clear at the procedural level: the agent is told this is a two-call flow, that the first call is non-mutating, and that the second call happens only after the human agrees to the summary. The gap is that no guidance is offered on when to prefer this over cancel/archive/delete of the same event, which is the main selection decision an agent faces among these siblings.

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