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

Beyond the annotations (readOnlyHint: false, destructiveHint: false), the description adds meaningful behavioral context: the operation is additive, existing attachments are preserved, re-running is safe, already-attached ids are reported and left alone, and the tool only handles native-structure campaigns. It also discloses the destructive clearing behavior of add_and_edit_native_campaign_elements relative to extensions.

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 description is long but every section earns its place: aliases, keywords, the core conceptual reason the tool exists, usage conditions, exclusions, required inputs, behavior, an ordering caveat, and an example. It is structured with clear headers and front-loads the most important clarification that attaching is different from creating.

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 tool with three required parameters and meaningful ecosystem interactions, the description is complete. It explains the prerequisite (list_extensions), the native-vs-Precision distinction, the relationship to sibling tools like remove_extensions_from_native_campaign and add_and_edit_native_campaign_elements, and the additive re-run behavior. No critical calling context 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 100%, so the baseline is 3. The description reiterates that extension_ids must be internal ids from list_extensions and not externalId, but the schema already states this explicitly. The example call adds a small amount of practical clarity but does not substantially extend the schema's parameter documentation.

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 opens with a specific verb and resource: 'Attach existing library extensions (sitelinks, callouts, etc.) to a native-structure Google Ads / Microsoft Ads campaign.' It clearly distinguishes this binding action from merely creating an extension, and the 'WHEN NOT TO USE' section further separates it from Precision-structure workflows and from remove_extensions_from_native_campaign.

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?

There is an explicit 'WHEN TO USE' section with concrete user phrasings, plus a 'WHEN NOT TO USE' section naming alternatives: call list_extensions first if the id is unknown, use remove_extensions_from_native_campaign for removal, and direct Precision-structure users to the platform UI. The ordering caveat about add_and_edit_native_campaign_elements is also clear operational guidance.

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