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

Annotations already declare destructiveHint=true, readOnlyHint=false, and openWorldHint=true; the description adds genuinely new context with the confirmation gate for bid increases and the -100 exclusion semantics. However, it says nothing about whether unspecified device bids are preserved, what happens on partial failure, or permission requirements.

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 action and scope, then the two operational rules. Every clause carries information; only the parenthetical device list is slightly redundant with the parameter names.

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 an 8-parameter mutation tool with no output schema, the definition covers the action, the destructive sentinel, and the confirmation workflow, which is most of what an agent needs. The notable remaining gap is the targeting constraint (exactly one of campaign or ad group) that the zero-required-parameter schema leaves ambiguous.

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 38% (mobile_pct, tablet_pct, desktop_pct, campaign_id and ad_group_id have no schema descriptions), so the description carries extra weight. It clarifies the three device percentage fields and the -100 sentinel, but leaves the campaign_id vs ad_group_id selection rule, the 900 upper bound, and the account parameter unexplained.

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 (bid up/down) plus the resource (device bid adjustments on a campaign or ad group) and names the three device dimensions. This implicitly separates it from google_ads_set_keyword_bid and google_ads_update_campaign, but it never names an alternative outright.

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?

Gives a real gating rule ('Lowering runs directly; raising needs confirmation') and explains that -100 excludes a device, which tells the agent how to operate. It does not say when to pick this tool over sibling bid tools such as google_ads_set_keyword_bid, nor whether campaign_id or ad_group_id is required.

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