Inspect the classified diff for a built variant and flag substantive changes like numbers, claims, and CTAs so reviewers can see what changed before approval.
The classified diff for a built variant (MEDIA_CROP, TEXT_REWRITE, LINK_PLACEMENT, ORDER, DISCLOSURE, METADATA, FORMAT_OMISSION, ...). Substantive changes — numbers, claims, CTA — are flagged, never silent.
| Name | Required | Description | Default |
|---|---|---|---|
| variant_id | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden, yet it leaves out whether the call is read-only, whether it requires auth, and what happens if the variant is not built. The only behavioral claim – that substantive changes are flagged and never silent – is useful but narrow, and the meaning of 'substantive' is undefined.
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?
It is short and front-loaded, but the parenthetical category list is bulky and ends in '...', which signals incompleteness rather than precision. The two sentences do not waste words, but the first is jargon-heavy and the second is more slogan than specification.
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 should convey the shape of the result – the category list hints at structure but not whether the diff is field-level, per-sentence, or aggregate. For a diff tool with an undocumented parameter and no annotations, this is under-specified.
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?
The single parameter is variant_id, and schema coverage is 0%, so the description should explain its expected format and semantics. It only weakly implies variant_id must identify a built variant; it says nothing about ID format, source, or error behavior for unknown IDs.
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?
It names the resource (a classified diff for a built variant) and lists the change categories, but never states the verb explicitly – whether it computes, retrieves, or previews the diff is left implicit. It does not distinguish itself from siblings such as adapt_preview or content_get, so an agent cannot tell from this text alone which tool to call.
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?
There is no guidance on when to use this tool versus adapt_preview, variant_revise, content_get, or policy_check, and no mention of prerequisites (e.g. the variant must already be built). The 'built variant' phrase implies one precondition but does not state whether to call this before or after approval.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.