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

Annotations only declare the generic safety profile (readOnlyHint=false, destructiveHint=false); the description adds the operational traits that matter: it saves a private draft, runs Google validate-only, captures a complete affected-resource snapshot, and explicitly does NOT send the change. That is exactly the side-effect disclosure needed to decide whether to call it.

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?

Three tight sentences, front-loaded with the action and its effect, then the handoff. No filler, no restatement of the tool name, and the most decision-relevant fact ('does not send the change') is placed prominently.

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 prepare tool with no output schema, the description covers purpose, non-mutation guarantee, validation behavior, and the confirm handoff, so an agent has what it needs to call it. Minor gaps remain around what the saved draft exposes and how it relates to the approval_plan/task retrieval siblings, but nothing blocking.

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 33% (just customer_id), and the description adds no parameter-level meaning at all — it never mentions customer_id, asset_group_id, asset_id, or the field_type enum that determines which asset slot is targeted. With coverage well under 50%, the description was required to compensate and does not.

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 and resource ('Prepare to link an existing asset to a Performance Max asset group') and names the exact sibling it hands off to (google_ads_asset_group_link_confirm). An agent can distinguish this from the confirm tool and the other prepare/confirm pairs without opening any 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?

Explicitly names the follow-up tool and the gating condition: 'The confirmation tool is google_ads_asset_group_link_confirm; execution requires the user's agreement in the conversation.' This tells the agent both the alternative and when to route to it, rather than leaving the two-step pattern to inference.

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