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

Annotations already declare readOnlyHint, non-destructive and closed-world, so safety is covered; the description adds the meaningful operational constraint of 'at most 30 days per request'. It doesn't discuss rate limits or error behavior, but the output schema handles return shape.

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?

Front-loads the core purpose and constraint, then the sibling-routing sentence; no filler. The colon-list phrasing is dense but every clause carries scope information, though it reads telegraphically.

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 a full output schema and safety annotations present, the description need only cover scope, limits and routing, which it does. Minor gaps like multi-server behavior are left to the schema's server_name description.

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 baseline is 3, but the description adds real meaning beyond the schema: connector is characterized as 'events delivered to one destination' and attribution is tied to the 'v1 first-click attribution model', clarifying semantics the schema's short blurbs leave implicit.

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 ('pre-aggregated event counts from the v1 API'), enumerates available breakdown dimensions, and explicitly names what differentiates it from run_report (connector filter, v1 first-click attribution). An agent can distinguish it from siblings without opening the schema.

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?

Gives explicit when-to-use and when-not-to-use: connector filtering and first-click attribution select this tool, while 'Sessions, channels, landing pages, goals, period comparison and longer ranges' route to run_report. The 30-day cap further scopes appropriate use.

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