draft_responsive_search_ad

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

Description states non-destructive (does NOT create ad), but annotations readOnlyHint=false suggests possible side effects (e.g., saving draft). Not fully transparent about whether draft is stored or purely computed. Adds context but does not resolve the ambiguity.

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?

Well-structured: purpose first, then input details, then examples. Each sentence adds value. Slightly verbose but efficient overall.

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?

Covers purpose, input format, constraints, and next step. Output schema exists, so return value not needed. Lacks edge cases (e.g., what if headlines count invalid) but sufficient for a drafting 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 0% so description carries burden. Explains headlines/descriptions structure (plain string vs dict with pinning), valid pin values, and Google caps. Provides significant meaning beyond schema. Does not explain ad_group_id, final_url, or customer_id, but those are relatively self-explanatory.

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?

Clearly states the verb 'draft' and resource 'Responsive Search Ad', with explicit distinction from creation: 'returns a PREVIEW, does NOT create the ad'. Distinguishes from sibling 'confirm_and_apply'.

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?

Provides clear when-to-use (drafting preview) and explicit next step ('Call confirm_and_apply to execute'). Gives constraints (headlines 3-15, descriptions 2-4, character limits, pinning rules). Lacks explicit when-not-to-use or alternatives, but guidance is strong.

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