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

Goes well beyond the destructive/idempotent annotations: it discloses the more-than-doubling refusal guard, that the previous bid is returned so the change can be undone, that dryRun is free and cannot affect spend, and that automated bid strategies may make the setting moot. These are exactly the traits an agent needs before mutating live spend.

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?

Four sentences, no filler, and front-loaded: what it sets, then the guardrail, then the return value, then the bidding-strategy caveat. Every sentence carries distinct operational information.

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?

There is no output schema, and the description compensates by stating the return value (previous bid, for undo). Combined with the dryRun behavior, the large-change guard, and the bid-strategy caveat, an agent has everything needed to call this correctly on a destructive spend-mutating tool.

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 100%, so the baseline is 3, and the description earns a bump by explaining what cpcBid actually means functionally (the inherited default for keywords without their own bid) rather than just repeating the schema. The allowLargeChange and dryRun semantics it mentions are already fully spelled out in the schema, so it adds less there.

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 and scope: it sets the ad group's *default* max CPC, and immediately explains that this applies to keywords with no bid of their own, which cleanly separates it from msads_set_keyword_bid. An agent can pick between the two without opening either 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?

Gives concrete operating guidance: use dryRun when unsure, and set allowLargeChange only when the increase is deliberate and user-confirmed. It also warns that automated bid strategies may ignore the bid. It does not name msads_set_keyword_bid or msads_set_campaign_budget as alternatives, so sibling routing is implied rather than explicit.

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