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

Annotations already declare readOnlyHint=false, idempotentHint=false and destructiveHint=false, so the mutation profile is covered. The description adds genuinely new behavioral context beyond that: naming a label that does not exist creates it, and adding a label fires that label's own automations so one automation can cascade into another. It omits any note on ordering guarantees or what happens when the same action is added twice.

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 passage is short and the scoping constraint is front-loaded, but the prose is telegraphic to the point of being ungrammatical ('An action at the end of the automation, its wait after the step before'), which forces the reader to reconstruct the meaning. A small amount of connective wording would make it clearer without adding bulk.

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 7-parameter mutation tool with no output schema, the description covers purpose, action vocabulary, label-creation behavior and the automation-chaining side effect. It leaves unexplained what the call returns (no output schema exists to compensate), whether the action is always appended last, and what error conditions to expect for unknown sites or automations.

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 71%, and the description fills the most important gap: the bare 'label' parameter has no schema description, and the text explains that a new name becomes a label, which is a meaningful side effect. It also reinforces that circle is given by name and that the wait is measured after the preceding step, though it does not restate the wait_amount/wait_unit defaults that the schema already documents.

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 identifies the resource precisely as an action appended at the end of an automation on a named site, and enumerates the four concrete action types (add_label, remove_label, add_to_circle, remove_from_circle). It stops short of a clean verb+resource statement because the opening sentence is a fragment ('On one site of the account, named in site') and it never distinguishes this from the standalone add_to_circle/remove_from_circle siblings.

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 implied rather than stated: it says the action is 'at the end of the automation' and explains that a label added will trigger that label's automations, which hints at when chaining is desirable. However, there is no explicit when-to-use or when-not-to-use guidance, and it never says why an agent would pick this over the sibling add_to_circle or add_member_label tools.

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