Draft removing a conversion action

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

This is a case where the description carries far more than the annotations: it discloses that removal stops counting, drops the action from goal lists, preserves historical data while being irreversible, that SMART_CAMPAIGN_* and GOOGLE_HOSTED types are rejected with MUTATE_NOT_ALLOWED, and that a plan_id preview is returned. Annotations (destructiveHint=false, readOnlyHint=false) only say the draft itself is a safe non-write, which the description's preview semantics corroborate rather than contradict.

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 purpose is front-loaded in a single bolded line, follow-on sentences each add a distinct constraint (irreversibility, type restrictions, preview/apply flow) with no filler. The trailing Google Ads API documentation link is boilerplate that doesn't earn its place, keeping this just short of a 5.

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 an output schema covering the plan_id preview and annotations covering the safety profile, the description supplies everything else an agent needs: the irreversibility caveat, the rejecting conversion-action types, and the required confirm_and_apply follow-up.

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%, so both parameters (customer_id and conversion_action_id, including the GAQL hint for obtaining the ID) are already fully documented in structured data. The description adds nothing about parameter format or defaults, so the baseline 3 applies.

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 lead sentence gives a specific verb and resource ('Draft a REMOVAL of a ConversionAction') plus the critical qualifier that it returns a PREVIEW, which cleanly separates it from draft_create_conversion_action, draft_update_conversion_action, and the direct remove_entity sibling.

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?

It states the two-phase workflow explicitly ('nothing changes until confirm_and_apply applies it') and names the sibling that completes the operation, which is strong routing guidance. It does not, however, contrast this draft path against the direct remove_entity tool in the sibling list, leaving that choice to inference.

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