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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=false), so the description's contribution is semantic: it discloses the aggregation caveat that 'distinct people are never summed across groups' and the null-preservation rule for unavailable counts. These are real behavioral facts an agent cannot derive from annotations, though permission requirements and pagination/ordering behavior remain unstated.

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 dense sentences with no filler, and the operation plus its bounds are front-loaded before the return-value caveats. Every clause carries distinct information: cardinality limits, time ranges, currency/freshness, null handling, and the distinct-people aggregation rule.

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 an output schema already documenting return shape, the description supplies the constraints and caveats an agent needs to call it correctly. Minor gaps remain around result ordering relative to input groups and handling of invalid or unauthorized campaign IDs.

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?

With 0% schema description coverage, the description must carry parameter meaning, and it largely does: campaignGroups is explained as an outer group list of up to ten containing up to twenty campaign IDs, range is enumerated as 7/30/90 days, and artistId is characterized as 'one artist' scoping. It does not restate the UUID format or the 30d default, so the compensation is strong but not exhaustive.

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 and resource ('Compare up to ten groups of campaigns belonging to one artist') and immediately bounds it with concrete cardinality and per-entity limits (10 groups, 20 campaign IDs each). This is clearly distinct from siblings like dynamoi_get_campaign, dynamoi_list_campaigns, and dynamoi_get_campaign_management, which operate on single campaigns or campaign lists rather than grouped comparisons.

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 comparison framing and the explicit range options ('over 7, 30 or 90 days') give an agent a clear sense of when this tool applies versus single-campaign retrieval. However, it names no alternative tool and states no exclusions, so the agent must infer that per-campaign detail should route to dynamoi_get_campaign.

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