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 supplements this with useful behavioral context: supported channels, timeframe shorthand and default (current month), and the full set of exposed metrics, all beyond what annotations provide.

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 uses compact labeled sections (USE FOR, NOT FOR, CHANNELS, TIMEFRAME, METRICS), front-loads the core grouping behavior, and contains no filler. The longer METRICS list is justified because it informs both sortable fields and expected return dimensions.

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 read-only stats tool with no required parameters, this is largely complete: grouping, channels, timeframes, defaults, metrics, and sibling routing are all covered. The only notable gap is that no output schema exists and the description does not describe the exact response envelope, though the metric list substantially mitigates this.

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 the baseline is 3, but the description adds real value by enumerating valid channels, documenting timeframe variants like 'last two months' and 'last 20 days', listing available metrics, and noting the default current month. This goes beyond the schema without contradicting it.

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 opens with 'Performance metrics grouped by Country', giving a specific verb, resource, and grouping dimension. It also explicitly distinguishes itself from sibling tools: account-level aggregates should use account_level_stats, campaign-level details use experiment_performance_stats, and ingredient-level uses performance_metrics.

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 USE FOR section enumerates concrete scenarios: performance by country/geography, country-level spending/conversions, geographic comparison, international campaign effectiveness, and regional ROI/pipeline. The NOT FOR section names the exact alternatives to use instead, leaving no ambiguity about when to choose a sibling tool.

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