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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the agent knows this applies a mutation; the description usefully adds that the change must be pre-prepared and that a plan digest plus the complete expected_changes must be supplied, hinting at a verification guard. It does not say what happens on digest mismatch, whether the operation is idempotent or reversible, or what entity the enable applies to.

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?

A single sentence that front-loads the action and then the two invocation paths, with no filler. It is slightly dense and the two modes run together, but nothing 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?

For a destructive, six-parameter confirm tool with no output schema and sparse schema descriptions, the description covers the invocation mechanics but leaves the agent without the entity being enabled, the prepare-prerequisite linkage, or failure/reconciliation behavior. Adequate to call it correctly, incomplete to call it confidently.

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 only 17% (just customer_id), so the description carries most of the burden, and it does: it names five of six parameters and explains the mutually exclusive draft_id vs approval_ref + expected_plan_digest modes plus the 'complete expected_changes' requirement. It omits connection_context entirely and gives no format detail for expected_changes, keeping it below a 5.

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 gives a specific verb ('Confirm') and a specific resource ('a prepared change'), and the parameter routing sharpens the intent further. It never states what is actually being enabled (the status-enable semantics live only in the tool name), and it does not distinguish itself from the many sibling *_confirm tools, so it stops short of a 5.

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 phrase 'a prepared change' implies the corresponding prepare step must run first, and the two alternative identifier paths (draft_id vs approval_ref + expected_plan_digest) give real invocation guidance. However, it never explicitly names the prepare sibling, states prerequisites, or says when to prefer this over google_ads_status_pause_confirm or the generic approval_plan_confirm, so usage is only implied.

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