set_keyword_bid

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

Goes well beyond the destructive/idempotent annotations by disclosing concrete guardrails: a 50% per-step bid move cap, a 0.10 minimum, a 20-actions-per-day rate limit, and a live-bid read before writing with a fail-closed behavior. This is exactly the operational context an agent needs before invoking.

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?

The 'PREVIEW ONLY' mode and the action are front-loaded, and every sentence carries weight. The guardrail sentence is dense with nested parentheticals, which is slightly heavy but justified by the complexity being disclosed.

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 mutation tool with no output schema, it covers guardrails, failure behavior, id sourcing, and the approval requirement. It does not explain the return/pending-status shape, but the preview/confirm workflow is clear enough for correct invocation.

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?

At 50% schema coverage, only amount and keywordId are documented in the schema. The description adds useful constraints on amount (min 0.10, 50% step) and points to get_ads_keywords for keyword/campaign ids, but says nothing about the undocumented currency parameter. Baseline 3 for partial coverage.

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 ('set the bid of one Apple Ads keyword') and front-loads the 'PREVIEW ONLY' mode. This cleanly distinguishes it from siblings like set_daily_budget and pause_keyword, so an agent can select it without opening 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?

Gives clear context: ids come from get_ads_keywords, and the action should only be applied with the user's explicit approval, implying a preview-then-confirm flow. It stops short of explicitly naming the confirm/apply sibling or stating when NOT to use it, so it falls just under full marks.

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