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

Annotations already cover read-only, idempotent, non-destructive, and closed-world behavior. The description adds meaningful analytical context: components are impression-weighted and the output names worst-scoring high-spend keywords, which goes beyond the safety 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?

Three tight sentences, front-loaded with the core operation and component list, followed by the analytical payoff. No wasted words.

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 purpose and analytical behavior are well covered, and the output schema handles return values. However, six parameters at 0% coverage are entirely unaddressed, so the agent lacks guidance on scoping, grouping, and detail level.

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?

There are six parameters with 0% schema description coverage, and the description mentions none of them. It does not explain days, detail, render, group_by, max_findings, or customer_id semantics, leaving the agent to infer behavior from enum values and defaults alone.

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 names the specific resource (Quality Score) and the exact operation (break down into expected CTR, ad relevance, landing-page experience), and adds impression weighting plus worst high-spend keyword identification. This clearly distinguishes it from siblings like account_health_score, full_audit, and bidding_audit.

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?

It implies diagnostic usage by saying it identifies which component is dragging the account down, but it never states when to choose this over account_health_score, full_audit, or bidding_audit. No exclusions or prerequisites are given.

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