Find high-impression, low-AI-traffic pages

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is fully covered. The description adds a useful privacy guarantee ('GA4 data stays in this local MCP process') which is the primary behavioral addition. It doesn't describe return format, thresholds logic, or error handling, but the annotations carry the main burden and the description adds the meaningful local-processing note.

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 sentences, front-loaded with the core purpose, minimal waste. Every clause contributes: what it pulls, what it returns, and the privacy note. No redundant framing or repetition of schema details.

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?

With 9 parameters and 100% schema coverage, the description explains the core workflow without needing to list every param. It lacks an output schema so it doesn't detail the return structure, but for a complex multi-input matching tool the description is complete enough to select and invoke. The distinction between CSV and rows inputs plus the privacy guarantee covers the non-obvious aspects.

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 100%, so the schema documents all 9 parameters. The description adds value by explaining the matching logic ('match them with an aggregated GA4 CSV or GA4 rows'), which clarifies how ga4_csv, ga4_rows, and source interrelate. It also conveys the filtering intent behind maximum_ai_traffic and minimum_bing_impressions beyond their raw schema descriptions. Marginally above baseline 3 due to the workflow framing.

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 title and description clearly state the purpose: find pages with high Bing impressions but low AI-referral traffic. The verb 'find' plus the specific resource ('high-impression, low-AI-traffic pages') and the mechanism ('Bing top-page statistics matched with GA4 data') make it specific and it clearly distinguishes from sibling bing_* tools by combining Bing stats with GA4 data.

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 explains the tool pulls Bing's top-page statistics and matches with GA4 CSV or GA4 rows, giving clear context on data inputs. It doesn't explicitly state when-not-to-use or name alternatives, but the 'GA4 data stays in this local MCP process' adds a privacy-relevant usage note. Lacks explicit exclusions versus sibling AEO tools but the workflow is clear enough.

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