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

Annotations already declare destructiveHint=true and openWorldHint=true, so the safety profile is carried by structured data. The description adds that unlinking is done by asset ID and field type, but its closing phrase 'Runs directly' is ambiguous — it is unclear whether this means live execution without confirmation or something else, and the dry_run option is never mentioned despite the mutation being destructive.

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?

Two compact sentences, front-loaded with the primary action before covering removal. The trailing 'Runs directly' is the one piece of wording that does not clearly earn its place given the ambiguity.

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 10-parameter mutation with no output schema, the definition covers what gets added and removed but omits preconditions (an existing asset group), the meaning and value of dry_run, account resolution, and what a call returns or how partial failures are reported.

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 across 10 parameters, the description does useful work by clarifying that images are https URLs and that removal takes asset_id plus field_type. However, it never explains account, dry_run, or the distinction between logos, square_images, and landscape_images, nor the per-field caps enforced in the schema.

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 pair (add/unlink) and a specific resource (Performance Max asset group assets), enumerating the asset types handled (headlines, long headlines, descriptions, images). It is clearly a PMax-scoped tool, but it does not distinguish itself from nearby siblings such as google_ads_add_assets, google_ads_add_more_assets, or google_ads_remove_assets, which an agent would need to choose between.

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?

No when-to-use guidance is given: nothing says whether this supersedes google_ads_add_assets for PMax or whether asset IDs for removal must first be listed via google_ads_assets. The only implicit hint is that removal requires an asset ID plus field type, leaving the agent to infer the workflow.

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