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

Annotations already flag destructiveHint=true, but the description adds genuinely new context: this is an unlink rather than a delete, so the asset stays in the library and remains reusable. 'Runs directly' signals immediate execution without a confirmation step, which matters for a destructive tool. It does not mention rate limits, reversibility of re-linking, or the dry_run escape hatch.

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 short sentences with zero filler. The action and its scope come first, the non-destructive consequence second, and the execution mode last — well front-loaded.

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 mutation tool whose annotations already carry the safety profile, the description supplies the critical nuance that assets remain in the library and execute immediately. Minor gaps remain around the 50-asset limit, dry_run usage, and whether unlinking affects historical reporting, but nothing essential to calling it correctly is missing.

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 75%, so the schema already documents account, campaign_id, and dry_run. The description reinforces that removal is keyed by asset ID plus type, which maps to the required 'assets' array, but adds nothing about the 50-item maxItems cap or the dry_run option. Baseline 3 is appropriate.

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 uses a precise verb ('Unlink') with the resource (assets), enumerates the coverable asset types, and states both scopes (campaign or account). It is clearly distinguishable from google_ads_assets, which it names as the lookup companion, though it does not explicitly contrast with generic google_ads_remove or google_ads_add_assets.

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 by the verb and by the pointer to google_ads_assets for finding asset IDs, plus the note that assets persist in the library. There is no explicit when-not guidance, no mention of the dry_run validation path, and no stated preference between the campaign-level and account-level modes.

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