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

Annotations declare destructiveHint=true / readOnlyHint=false, so the mutation risk is already signalled. The description adds real behavioral value beyond that: the preview-unless-confirmed dry-run flow, the real-currency unit convention, and the warning emitted when a target is set with too few conversions to learn from. It stops short of saying what the change overwrites or whether the prior strategy is recoverable.

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?

One compact sentence enumerates the strategies, followed by three short sentences covering units, the learning warning, and the preview/confirm gate. No filler, and the core operation is front-loaded.

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 destructive, open-world mutation tool with no output schema, the description covers the dry-run default, the commit flag, money units, and a failure mode (insufficient conversions). What remains thin is confirmation semantics beyond the flag and the absence of any sibling disambiguation against ads_campaign_bidding.

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 coverage is only 43%, so the description must compensate, and it does: it maps each optional numeric target to the strategy it belongs with (target CPA for Maximize conversions, ROAS for Maximize conversion value, max CPC for Maximize clicks) and clarifies monetary units as real currency. The required identifiers customer_id and campaign_id are left 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+resource ('Change a campaign's bidding strategy') and enumerates the four supported strategies with their optional targets, so the agent knows exactly what operation this performs. It does not, however, distinguish itself from the sibling 'ads_campaign_bidding', which by name sounds like it could do the same thing.

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?

The description explains the invocation contract (preview by default, confirm=true to apply) which is genuine usage guidance, but says nothing about when to choose this tool over 'ads_campaign_bidding' or other bidding-related siblings, nor about prerequisites such as campaign existence or required account permissions.

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