Compare a proposed vilsem visual with a saved version for a read-only JSON Patch diff, before/after PNGs, and critique before replacing a design.
Read-only comparison against one saved vilsem visual: JSON Patch diff and before/after live PNGs with critique. This writes no files. Run before replacing an existing design.
| Name | Required | Description | Default |
|---|---|---|---|
| spec | Yes | ||
| pageName | Yes | ||
| reportDir | Yes | ||
| visualName | Yes | ||
| connectionId | No |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does disclose the safety-relevant facts: it is read-only and writes no files. It also lists the return artifacts (patch diff, PNGs, critique). However, it omits what happens if the visual doesn't exist, that live rendering costs time/side effects, and any permission requirements.
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 short sentences, front-loaded with purpose and output artifacts, then the safety and usage cues. 'This writes no files' mildly repeats 'Read-only' but serves as deliberate emphasis rather than padding.
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?
The description covers outputs and the non-destructive behavior well, which matters since there is no output schema. But for a five-parameter tool with a nested spec object, zero schema description coverage and no annotations, the total absence of parameter guidance leaves the definition materially incomplete.
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 0% across five parameters (reportDir, pageName, visualName, spec, connectionId), and the description explains none of them. Notably the required 'spec' object and optional 'connectionId' are entirely opaque to the caller, so the description does not 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 states a specific verb and resource ('Read-only comparison against one saved vilsem visual') and names concrete outputs (JSON Patch diff, before/after live PNGs with critique). It doesn't explicitly name a sibling tool, but the phrasing clearly separates it from validate_/preview_/update_ tools by emphasizing comparison against an already-saved visual.
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?
'Run before replacing an existing design' gives a clear usage context that implicitly routes the agent away from update_visual/commit_visual until a diff has been inspected. It stops short of naming alternatives or stating when not to use it (e.g., when the visual does not yet exist).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.