before_after

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

With no annotations, the description carries the full burden, and it does disclose output content (two images plus score/metrics) and defines the 'original' semantically via build()/original(d). It does not clarify whether images are returned inline versus written to disk, or any side effects, permissions, or pagination concerns.

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?

Three sentences, front-loaded with the output, then defining 'original', then the export relationship – each sentence carries distinct information. It is somewhat jargon-dense ('build() loads with import_model', 'original(d)') but not padded.

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 usefully explains what is returned (image pair plus compare score/metrics) and clarifies the ambiguous concept of 'the original'. However, four entirely undocumented parameters leave the calling contract incomplete for an agent that must supply them.

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 0% and the four parameters (name, size, inline, variant) have no titles beyond their names and no descriptions. The description never explains what name identifies, what size values mean, what inline controls, or what variant selects, so it fails to compensate for the coverage 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?

The description concretely states what the tool produces – the original and remix images side by side, a deviation-colored original, plus compare's score and metrics – which is more than a name restatement. It implicitly distinguishes itself from the compare sibling by describing it as the visual companion to compare's deviation view. It never uses an explicit verb like 'render' or 'generate', so the action framing is slightly indirect.

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 opening 'For a remix' scopes when this applies and the mention of 'export writes the same two images when it writes PNGs' hints at an alternative path, but there is no explicit when-to-use / when-not-to-use guidance versus compare, render_preview, or export. Usage is implied rather than stated.

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