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

Annotations already declare destructiveHint=true and openWorldHint=true, so the bar is lower, and the description still adds real behavior: new groups are created in PAUSED state, and enabling is a gated action needing confirmation. It does not explain what an update overwrites or whether omitted fields are preserved, which is the main remaining gap for a destructive mutation.

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?

A single front-loaded sentence that covers both modes without padding, and the parenthetical confirmation note is placed where it matters. The density of parentheticals makes it slightly harder to parse but nothing is wasted.

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 17-parameter destructive mutation with no output schema, the description is thin: it omits the required field combinations per action, the asset-type arrays beyond a generic 'texts and images', and any mention of the dry_run safety path that exists in the schema. An agent could not construct a valid 'add' call from this description alone.

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 only 18% across 17 parameters, so the description must compensate and largely does not. It gestures at 'texts and images' and names final URL and status, but leaves campaign_id, asset_group_id, business_name, search_themes, and the headline/description/image array limits entirely undocumented, and says nothing about which fields are required for 'add' versus 'update'.

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 names two concrete operations on a specific resource: 'Add a new asset group ... to an existing Performance Max campaign' and 'update an asset group's name, final URL or status'. That is far more specific than the title alone, though it never distinguishes this from siblings such as google_ads_pmax_assets or google_ads_add_assets.

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?

It implies a prerequisite (the Performance Max campaign must already exist, so creating one is a different tool) and flags that enabling requires confirmation. It gives no explicit routing against the many other asset-related siblings, so the agent must infer when to pick this versus google_ads_add_assets or google_ads_set_asset_status.

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