performance_summary

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

Annotations already indicate readOnlyHint=true and destructiveHint=false. The description adds behavioral context: it is for triage, not causal analysis; results have caveats; campaign records include metric values and heuristic flags. No contradiction with 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 well-structured with Args/Returns sections and usage guidance, but it is somewhat lengthy. A slightly more concise version could improve readability.

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?

Given the tool's complexity (multiple parameters, heuristic flags, return envelope), the description is complete: it explains the return format, read-only nature, caveats, and provides guidance on when to use. No gaps are evident.

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 input schema has detailed descriptions for all sub-parameters, so schema_description_coverage is effectively 100%. The tool description merely lists the parameters without adding meaning beyond the schema, so baseline 3 is appropriate.

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's action: 'Rank campaign performance and flag heuristic symptoms for review.' It specifies the resource (campaigns) and differentiates from sibling tools like list/get operations, as this is a summary/analysis tool.

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: 'Use this for read-only campaign triage, not as proof of causation or a verified diagnosis.' It also warns against using for delivery changes or asserting causal impact, and explains limitations of platform-reported metrics.

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