Classify previs issues by severity, identify the violated rule, and return fix priority from an error description.
Classify a previs error by severity level (FATAL, STRUCTURAL, or POLISH). Provide a description of the issue and get the severity classification, the specific rule it violates, and the fix priority.
| Name | Required | Description | Default |
|---|---|---|---|
| error_description | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections.
v1.5.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden. It discloses the shape of the result (severity, violated rule, fix priority), but says nothing about whether the call is a stateless read-only classification, whether it logs or mutates project state, or how it handles descriptions it cannot classify.
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 lines, front-loaded with the classification vocabulary, and zero filler. Slight redundancy in the second sentence restating the severity output already named in the first.
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 one-parameter classification call with an output schema available, the description covers purpose, input intent, and the nature of the response. Only the usage trigger and side-effect profile are left unstated, which is a modest gap at this complexity level.
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% — the single parameter is documented only by its title. The description partially compensates by telling the agent to 'provide a description of the issue', implying free-text problem statement, but adds no guidance on granularity, format, or whether structured context (scene, rig, phase) should be embedded.
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?
States a specific verb (classify) and resource (previs error) and enumerates the output domain (FATAL, STRUCTURAL, POLISH), which makes the tool's job unambiguous. It does not explicitly contrast with the similarly-named sibling classify_character, so an agent must infer the distinction from the 'previs error' phrasing.
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?
Usage is only implied: the agent should call this when it has an error to triage. There is no statement of when not to use it, no prerequisites, and no routing to alternatives such as get_previs_help or validate_gate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.