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

Annotations already establish readOnlyHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is covered without description help. The description usefully discloses an analytical behavior the annotations cannot convey: fatigue detection is a cross-period comparison ('rising frequency with falling CTR vs the previous period'), which tells the agent the tool performs period-over-period math rather than a point-in-time snapshot. It says nothing about return shape, whether both extremes are always present, or minimum spend/impression thresholds for ranking.

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?

A single sentence with the core action front-loaded and the qualifier about fatigue appended after the primary metrics. Every clause carries information; there is no filler or restatement of the 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?

For a read-only analytics tool with zero required parameters, 100% schema coverage and no output schema, the description gives enough to know what question it answers and what signals come back. The gap is that it never sketches the returned structure (ranked rows, sections, which metrics beyond cost per result and CTR), leaving the agent to guess at output shape.

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% and all seven parameters carry inline descriptions, including the summary/full enum trade-off and the date_range default, so the schema does the heavy lifting. The description adds no parameter-level meaning of its own. Baseline 3 applies when structured fields fully document the inputs.

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 opens with a specific verb+resource combination ('Rank ads by efficiency') and enumerates the exact outputs: best and worst creatives by cost per result and CTR, plus fatigue signals. That is far more concrete than the bare name 'meta_creative_insights'. It stops short of naming the sibling it displaces (e.g. meta_ads or meta_insights_query), so an agent must infer the boundary from the metric set alone.

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 use case ('best and worst creatives', 'fatigue signals') is implied by the output description, so an agent can infer this is the tool for creative-level efficiency questions. However, there is no explicit when-to-use statement, no exclusions, and no named alternative such as meta_insights_query for general metric pulls or meta_ads for the raw ad list.

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