cross_preset_ab_report

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

No annotations are provided, so the description carries the full burden - and it only discloses the paywall gate ('Requires Kiln Pro' with an upgrade URL). The remaining sentences are an unrelated feature catalogue ('calibration that learns your printer, mid-print edits, unlimited textures') that says nothing about what the analysis does, how much data it scans, or whether it fails when a preset has too few outcomes.

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?

Only the first fragment serves the tool's purpose; the next three sentences are pricing/upsell boilerplate and a feature list unrelated to cross-preset A/B analysis. The useful prerequisite is buried in the middle of the marketing copy instead of being front-loaded.

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 two-parameter analysis tool with no annotations and no output schema, the description should at minimum explain the input contract and what the report contains. Instead it spends its length promoting the Pro tier, leaving an agent unable to construct valid preset_inputs.

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 50%: min_outcomes_per_preset is documented in the schema, but preset_inputs is a bare untyped array with no description. The description adds nothing about either parameter - not the expected shape of a preset input, how many presets are expected, or the default of 3 outcomes per preset.

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 opening line 'Cross-preset outcome A/B analysis' names the resource (presets) and the activity (A/B outcome comparison), so an agent can infer this compares outcomes across presets. However it never explains what a 'preset input' is or how it differs from the sibling tools cross_branch_ab_report and cross_feature_ab_report, leaving the scope of the comparison ambiguous.

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 only guidance offered is the entitlement note 'Requires Kiln Pro', which is a prerequisite rather than a when-to-use rule. Nothing tells the agent when to pick this over cross_branch_ab_report or cross_feature_ab_report, nor what happens if the Pro plan is absent.

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