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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds the sort order (highest spend first), which matters for interpreting truncated results, but says nothing about truncation behavior, row limits, or empty-result handling beyond the schema.

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?

One dense, front-loaded sentence: geography scope first, then time scope, then optional filter, then metrics and sort. No filler, though packing the whole metric list into the sentence makes it slightly run-on.

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?

There is no output schema, so the description usefully enumerates the returned metrics (impressions, clicks, CTR, average CPC, cost, conversions) and declares sort order. Combined with full schema coverage of the five optional parameters, an agent has enough to call it; only result-shape details such as grouping granularity are left implicit.

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 description coverage is 100%, so date formats, defaults, account id format and the campaign id source are all already documented. The description only restates the date range and optional campaign scoping, adding no semantics beyond the schema; baseline 3 applies.

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+resource+dimension: performance broken down by searcher geography (country and city) for a date range, optionally scoped to one campaign. That is distinguishable from msads_get_campaign_performance or msads_get_keyword_performance, though siblings are never named explicitly.

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 'optionally one campaign' and 'for a date range' imply the filtering use case, and the metric list implies a reporting/analysis use case. But there is no explicit when-to-use guidance and no routing away from sibling performance tools such as msads_get_campaign_performance or msads_get_ad_group_performance.

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