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

Annotations already declare readOnly=false, idempotent=false, destructive=false, openWorld=true, so safety is covered. The description adds real value beyond that: the prerequisite that the asset must already exist and the resource name comes from create_*_asset tools, plus the account-eligibility caveat for AD_IMAGE. It omits what happens on a duplicate link (relevant given idempotentHint=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?

Front-loaded with the action, then workflow context, then a well-structured Args block. Minor redundancy: the first sentence already states the link, and the second paragraph restates "attach it to an ad group," though it earns its place by adding the ordering constraint.

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?

Output schema exists, so the Returns line is a small bonus rather than a necessity. For a four-parameter mutation, the description covers preconditions, parameter formats, and the tricky field_type enumeration. It could still mention duplicate-link behavior or required permissions, 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 0% (all four properties have only titles), so the description carries the full burden and does: format constraint ("numbers only, no hyphens") for customer_id, semantics for ad_group_id, provenance for asset_resource_name, and a full enumerated list of valid field_type values with an eligibility note for AD_IMAGE.

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 ("Links an existing asset to an ad group") and scopes it further with the second sentence explaining the effect (asset appears with that ad group's ads). The ad-group target distinguishes it from the sibling scope variants link_asset_to_campaign and link_assets_to_customer.

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 states the precondition and workflow position: "After creating an asset (sitelink, callout, etc.), use this tool to attach it to an ad group." It does not, however, name the sibling alternatives (campaign-level or customer-level linking) or say when to choose them, leaving that routing to inference.

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