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

Annotations already flag destructiveHint=true, idempotentHint=true and openWorldHint=true, and the description adds substantive context beyond them: it discloses that the existing adjustment is replaced immediately, that raising exposure increases spend, and that out-of-range values are rejected before any call is sent. That is exactly the kind of consequence and validation behavior an agent needs before mutating live bids.

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?

It is front-loaded with the action, then the risk warning, then semantics, then args — a sensible order. There is minor redundancy: the sentence 'Raises or lowers the campaign's bids on Mobile, Desktop or Tablet' restates what the device_type arg documentation already lists, and the Returns block duplicates the existing output schema.

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 four-required-parameter mutation with an output schema, the description is nearly complete: it covers units, allowed values, immediate effect, and rejection of invalid input, so the Returns section is unnecessary given the output schema. The one remaining gap is that it never states permission or campaign-state prerequisites (e.g., whether the campaign must be enabled for the adjustment to take effect).

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 0% — the schema carries only titles — so the description must do all the work, and it does: customer_id is numbers-only without hyphens, device_type is constrained to MOBILE/DESKTOP/TABLET, and bid_modifier's allowed range (0 or 0.1–10.0) is spelled out with a multiplier-to-percentage mapping table. This fully compensates for the empty schema.

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 first sentence states a specific verb ('Sets'), a specific resource ('bid adjustment'), and a precise scope ('for a specific device type on a campaign'). That scope alone distinguishes it from broad siblings like update_campaign or set_campaign_status, so an agent can route to it without inspecting the schema.

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 gives real usage context: it warns that any value above 0 on an excluded device can expand reach and spend, and it explains the two regimes (0 = stop bidding, 0.1+ = resume). It does not name an alternative tool or state when-not-to-use (e.g., versus editing device targets through update_campaign), so it stops short of fully explicit routing.

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