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

Annotations only declare destructive/openWorld/not-readOnly; the description adds substantial behavior beyond them — prior comments are never answered, arming binds to the first post at its first comment, arming is paid with one armed automation per account, plan-limit accounting, and the published-page requirement.

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?

Front-loaded with the core action, then structured bullets per mode. It is long, but nearly every sentence carries non-obvious state-machine behavior, so little is wasted.

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?

Output schema exists, so return values need no explanation. For a stateful activation tool, the description covers both branches, edge cases (conflicting keyword → draft), billing constraints, and preconditions.

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?

Single required parameter with 100% schema coverage, so the baseline is 3. The description references provider_media_id (an attribute of the automation, not an input to this call) to explain mode selection, but it adds nothing about automation_id itself.

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 ('turn on') and resource ('automation'), and immediately distinguishes the two modes (on a post vs. armed without a post). An agent can separate this from pause_automation, create_automation, or delete_automation without opening a 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?

Explains in detail when each mode applies (with provider_media_id vs. without) and what happens at binding time. It does not explicitly name the sibling to choose instead when a user wants the opposite (pause/disable), so routing is implied rather than spelled out.

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