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

Annotations already declare readOnly, idempotent, non-destructive, and open-world, so the safety profile is covered. The description adds genuinely useful context: it costs no Adrails credits and returns structured content including metadata-gap diagnostics. However, it says nothing about data freshness, time window, or pagination behavior for the returned insights.

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?

The core sentence is front-loaded with the grouping mechanism and the output list, followed by a clean usage sentence. The MCP/credits line is boilerplate but short and informative; nothing is padded or redundant.

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 no output schema, the description carries the return-value burden and does so by enumerating winners, fatigue, repeated usage, hook/hold rates, and metadata gaps. Annotations cover safety and the schema covers most params, leaving only minor gaps like the analysis window.

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 75%, so the schema largely documents accountIds, userStatement, and idempotencyKey itself. The description contributes nothing about limit, accountIds narrowing, or the nested input object beyond a harness boilerplate line, so it does not compensate for the remaining gap.

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 and resource: "Groups Meta ads by the actual image or video asset," including the cross-ad/cross-account scope, which is a non-obvious capability. It then enumerates outputs (winners, fatigue, hook/hold rates, metadata gaps), so an agent knows exactly what it gets, though it never names a sibling it differs from.

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?

"Use this before proposing creative variants or comparing hooks" gives concrete triggering conditions. There are no explicit exclusions or named alternatives (e.g., when to prefer creative_review or creative_market_evidence), so it stops short of full routing guidance.

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