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

Annotations already cover the safety profile (readOnlyHint=true, openWorldHint=true, destructiveHint=false), so the description's remaining job is to add context it does not supply: no mention of what metrics come back per row, no row-count or date-span limits, no note that folder and account are alternatives. It only restates the dimension list, adding essentially nothing behavioral beyond the annotations and schema.

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?

Two short clauses, front-loaded with the primary capability and free of filler. It is efficient, though the telegraphic phrasing ('Performance split by...') reads as a fragment rather than a structured statement of intent.

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 7 parameters, 86% schema coverage, and no output schema, the structured fields carry most of the load and the description needs to cover return values and routing. It does neither: no indication of which metrics appear per breakdown row, and no guidance on choosing this over the many sibling reporting tools.

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 86%, so the parameters are already documented (folder vs account, date_range default LAST_7_DAYS, start/end date pairing, campaign_id). The description adds no new meaning beyond repeating the enum values and the campaign filter, so the baseline 3 applies.

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 resource (performance) and the exact split dimensions, which line up one-to-one with the `by` enum (device, date, day of week, hour, location, age, gender). An agent can tell this is the per-dimension reporting tool rather than the aggregate one, though it never names `google_ads_performance` or `google_ads_ad_performance` to sharpen the contrast.

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?

Usage is only implied: 'Optionally for one campaign' hints that narrowing scope is possible, and the dimension list implies 'use this when you want a per-segment split'. There is no explicit when-to-use versus `google_ads_performance`, `google_ads_placements` (a location/placement split), or `google_ads_ad_performance`, and no stated exclusions.

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