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

With no annotations the description carries the full burden, and it does disclose useful traits (scope limits, external spend-approval flow). However, it directly contradicts the schema enum: it says 'Activation' and 'bid changes' are unavailable while the enum exposes ENABLE and ADJUST_BID, leaving the agent unsure whether those calls fail or are merely discouraged.

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 tight sentences: the first front-loads the permitted actions, the second carries the restriction and its rationale. No filler, nothing buried.

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?

Covers the operation set and the spend-approval constraint for a mutation tool with no annotations or output schema. But the unresolved ENABLE/ADJUST_BID mismatch and lack of any note on outcomes or permission requirements leave real gaps.

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 80%, so the schema already documents campaignId, negativeKeywords (and its action dependency), and the cents-unit budget. The description reinforces which params correspond to budget/keyword changes but adds no new semantics (e.g., campaignId format or idempotency).

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 (manage) plus resource (Google Ads campaign) and enumerates the supported operations (pause, change daily budget, add negative keywords), which cleanly separates it from siblings such as google_ads_create_search_campaign and google_ads_get_campaign_insights.

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 frames when to use it (customer-created campaigns, pause/budget/negative keywords) and when not to (activation and bid changes), and names the alternative path for the excluded cases ('the customer approves spend on the Ads page').

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