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

Goes well beyond the destructiveHint annotation: it discloses that the asset is only unlinked ("stays in the library") and that the call previews unless confirm is true, a dry-run safety behavior not conveyed by any structured field. This directly clarifies how the destructive operation behaves.

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 clauses with zero filler: scope/semantics first, the use case second, the safety behavior last. Every sentence earns its place and the most important constraint is 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, no-output-schema mutation the description covers the critical behaviors: unlink semantics, the confirm gate, and account-vs-campaign scoping. Only the remaining parameter meanings (customer_id, field_type) are left to the schema, which is a minor gap.

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?

With only 20% schema description coverage, the description compensates for the two most consequential params: confirm (preview vs. execute) and campaign_id (omitted = account-level). It leaves customer_id and field_type unexplained, so its coverage of the 5 params is partial.

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 (unlink) and resource (extension asset), plus the scope variation (campaign vs. account when campaign_id is omitted). This clearly distinguishes it from ads_add_extensions and ads_list_extensions 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?

"Use it to retire an old phone number or sitelink" gives a concrete when-to-use scenario, and the campaign_id-omitted clause clarifies scope selection. However, it names no alternative tools or explicit exclusions, so guidance is clear but not fully routing.

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