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

Adds real behavioral context beyond the annotations: the >2x guard rail and how to override it, the fact that the previous bid is returned so the change can be undone, the dryRun preview semantics, and the caveat that automated strategies may nullify the bid. These are things an agent could not infer from destructiveHint/idempotentHint alone.

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?

Five short sentences, front-loaded with the core action and effect, then guard rails, then return/undo behavior, then usage advice and the bid-strategy caveat. Nothing is padded or repeated.

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 six-parameter mutation with no output schema, the description covers the action, the guard rail and its override, reversal via returned previous bid, and a safe preview path. An agent has everything needed to call it correctly and safely.

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 every parameter including allowLargeChange, dryRun, and currency handling is already fully documented in the schema. The description restates the doubling rule and dryRun but adds no syntax, formatting, or constraint detail beyond what the schema provides, so the baseline 3 applies.

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 and resource and narrows scope precisely: "Set one keyword's own max CPC bid." The phrase "one keyword's own" distinguishes it from the sibling tools that set ad group (msads_set_ad_group_bid) or campaign-level (msads_set_campaign_budget) values, and "This changes what the keyword can spend per click" nails the effect.

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 clear operational instruction ("Use dryRun first when unsure") and a meaningful exclusion condition (bids steer delivery under Manual/Enhanced CPC, but ";under an automated bid strategy Microsoft may ignore them"). It does not explicitly name the sibling alternative for ad-group or campaign-level bid changes, so the routing guidance is strong but not exhaustive.

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