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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=true, covering the safety profile, so the bar is lower. The description is consistent with those hints but adds little new behavioral context (no pagination/limit behavior, no auth or quota notes, no result-shape detail).

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?

Two tight sentences with no filler, and the core capability (metrics by geography) is front-loaded before the analytical use case. Every phrase earns its place.

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 five-parameter analytics tool with no output schema and 20% schema coverage, the description names the returned metrics but omits any mention of date-range semantics, result limiting, or how widely results can be grouped. Adequate but with clear gaps.

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 only 20%, so the description is expected to compensate. It does explain the most semantically interesting parameter by spelling out the region/city options for 'level', but leaves limit, startDate and endDate undocumented in prose. Partial compensation for a low-coverage schema.

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 specific metrics (cost, clicks, conversions, CPA) and the exact grouping dimension (country/region/city via level). This clearly differentiates it from the other *_performance siblings such as ads_device_performance or ads_campaign_performance. It stops short of naming which sibling to prefer for wasted-spend analysis, but the resource is unambiguous.

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 phrase 'Finds locations that burn budget without converting' implies a use case (wasted-spend localization), which is real guidance. However it gives no explicit when-to-use vs alternatives, no exclusion relative to the overlapping ads_wasted_spend sibling, and no stated prerequisites for date ranges.

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