Draft keywords

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

The description explicitly states that the tool does not add keywords and returns a preview, disclosing its non-final nature. This goes beyond the annotations (readOnlyHint=false) to explain the draft workflow.

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 description is concise, using two short sentences to convey the tool's purpose and workflow. It is well-structured with no redundancy.

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?

The description provides enough context by referencing the 'confirm_and_apply' tool and the workflow of drafting before applying. It effectively differentiates from sibling tools like 'add_negative_keywords' or 'draft_ad_group'. The existence of output schema reduces the need to describe return values.

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?

The description explains the structure of the 'keywords' parameter, specifying the required fields (text and match_type) and allowed match_type values. However, it does not describe 'ad_group_id' or 'customer_id', leaving those parameters undefined. With only one of three parameters described, the coverage is low and not fully compensated.

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 description clearly states the tool drafts keyword additions and returns a preview, distinguishing it from tools that actually add keywords. It names the specific resource (keywords) and the action (draft).

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 explicitly directs the user to call confirm_and_apply with the returned plan_id to execute, providing clear next steps. It also warns that no keywords are added immediately, guiding appropriate usage.

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