Draft negative locations

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

The description clearly states the tool returns a preview and does not apply changes immediately, which aligns with the destructiveHint=false annotation. It mentions the returned plan_id and the need to call confirm_and_apply to execute, making the two-step behavior fully transparent. No contradictions exist between the description and annotations.

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 brief and to the point, using only three sentences to convey the purpose, usage, and execution flow. It avoids unnecessary detail and is well-structured, making it easy for an agent to parse and act on quickly.

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 covers the core workflow, including the preview nature, the return of a plan_id, and the need for confirm_and_apply. It does not detail the output schema or error handling, but given the simple parameter set and the mention of a plan_id, it is sufficiently complete for the intended use. Minor gaps like assumed knowledge of campaign_id and customer_id prevent a perfect score.

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 semantics of geo_target_ids (numeric Google geo target constant IDs) but does not elaborate on campaign_id or customer_id. Since the schema provides no descriptions (0% coverage), the description only partially compensates. The purpose of customer_id and campaign_id is assumed rather than explicitly clarified, which could lead to misuse.

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 negative geo location additions and returns a preview, distinguishing it from direct modifications. It explicitly mentions the use case of excluding cities/regions while keeping broader targets, and references the separate confirm_and_apply tool for execution. This is a specific verb ('Draft') and resource ('negative locations'), making its purpose unambiguous even among sibling tools.

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 provides explicit guidance on when to use the tool: to exclude cities/regions from a campaign while retaining broader positive targets. It also specifies the required parameter format (numeric Google geo target constant IDs) and directs the user to call confirm_and_apply with the returned plan_id for execution. This leaves no ambiguity about the workflow or when this tool is appropriate.

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