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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description still adds real behavioral context beyond them: the row grain ('one row per campaign') and the freshness caveat that the recent ~3 days may be incomplete, which is exactly the kind of data-quality caveat an agent needs before reporting numbers.

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, zero filler, and front-loaded: purpose and metric set first, then grain and freshness caveat, then the exclusion list. Every clause earns its place and there is no restatement of the name or title.

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?

An output schema exists, so return shape needn't be explained, and pagination is covered in the schema. The description supplies the two things structured data doesn't: grain and a freshness/data-window caveat. Complete enough to call correctly, though it doesn't note whether historical backfill limits apply.

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 100%, so all ten parameters (dates, sort_by, limit/offset, filters) are already documented in the schema. The description adds metric vocabulary and the date-range framing but no parameter-specific syntax or defaults. Baseline 3 is correct when the schema carries parameter meaning.

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+scope: Sponsored Products campaign-level performance over a date range, with the metric set enumerated. The 'campaign-level' grain plus the Sponsored Products qualifier cleanly separates it from siblings like get_adgroup_performance, get_sb_campaign_performance, and get_sd_campaign_performance.

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?

Explicit when/when-not routing: 'Do not use for ad group, keyword, search-term, ASIN, or total organic+paid sales questions' names the near-miss siblings by dimension. Combined with the opening 'Use for...' clause, an agent can select or reject this tool without opening any schema.

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