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

Annotations already declare destructive=true, idempotent=false, and openWorld=true, so the safety profile is known. The description adds genuinely new context: assets only serve after Google approves them, and they apply only to campaigns without their own same-type assets. It stops short of warning that the link cannot be removed by re-running, or how duplicates behave given idempotent=false.

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 core purpose and effect are front-loaded in the first two sentences, and the Args block is compact rather than boilerplate. The middle sentence is slightly tangled ('can show at once, after Google approves them, in the ads of every running campaign'), and the Returns section duplicates an output schema that already exists.

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 three-parameter mutation with an output schema present, the description covers purpose, propagation behavior, approval latency, and all parameter meanings. What is missing is operational edge-case guidance — duplicate links, partial failures across a list of resource names — which matters given destructive=true and idempotent=false.

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 0%, so the description carries the full burden and mostly succeeds: customer_id is constrained to digits only with no hyphens, and field_type is enumerated with ten valid values that the schema leaves as a bare string with no enum. Only asset_resource_names is thin, restating the list without any format or example guidance.

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 plus the level at which the link applies: 'Links assets at the customer (account) level so they apply to all campaigns.' That level qualifier is exactly what separates it from link_asset_to_campaign and link_asset_to_ad_group in the sibling list, so an agent can choose correctly without opening the 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?

The second sentence explains the effective behavior (assets serve in every running campaign lacking same-type assets of its own), which implies when account-level linking is appropriate. However, it never states when NOT to use this versus link_asset_to_campaign or link_asset_to_ad_group, nor any prerequisite such as assets already existing or approval status.

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