Tool & function calling
AuraScore 85/100

Multimodal Prompt Enrichment and Safety Dispatch Brief

Define vision-language model tool orchestration to inspect, enrich, and safety-screen generation prompts.

Use this template when setting up an automated pre-generation pipeline where an agent invokes multimodal visual-QA and safety classifiers prior to triggering an image generation backend.

Template

Role: Principal Vision-Language Agent Engineer designing automated pre-generation validation systems.

Context

  • Vision-Language evaluation model: {{vlm_engine}}
  • Compliance and safety policy: {{safety_taxonomy}}
  • Pre-generation enrichment tools: {{prompt_enrichment_tools}}
  • Output resolution matrix: {{image_resolution_constraints}}
  • Retry and threshold logic: {{retry_policy}}
  • Target generation system: {{downstream_generator}}

Task

Author a technical brief defining how an autonomous agent calls {{prompt_enrichment_tools}} and {{vlm_engine}} to inspect, expand, and safety-check user inputs before routing to {{downstream_generator}}.

Method

  1. Analyze raw user prompts against {{safety_taxonomy}} to identify required validation tool calls.
  2. Construct the tool execution sequence for semantic expansion using {{prompt_enrichment_tools}}.
  3. Formulate the function definition for invoking {{vlm_engine}} on reference input images when provided.
  4. Establish deterministic parameter translation from natural language requests to {{image_resolution_constraints}}.
  5. Design threshold-based gates that determine whether prompt modification passes or triggers {{retry_policy}}.
  6. Detail the payload structure dispatched to {{downstream_generator}} upon successful tool execution.
  7. Document observability hooks to log tool execution latency and token overhead.

Constraints

  • MUST enforce strict binary pass/fail criteria for {{safety_taxonomy}} checks.
  • MUST NOT send uninspected prompts directly to {{downstream_generator}}.
  • Keep the total document length between 500 and 750 words.
  • Limit tool definitions strictly to the provided enrichment and inspection toolsets.
  • Ensure schema formats match standard JSON tool calling standards.

Output format

1. Tool Calling Sequence

Ordered workflow mapping raw user prompt ingestion to final generation dispatch.

2. Validation & Enrichment Function Signatures

Formal JSON schema definitions for safety screening, visual QA, and style descriptor expansion.

3. Policy Gating & Retry Protocol

Decision matrix specifying conditions under which {{retry_policy}} is activated.

Self-review

  • Confirm that all variables ({{vlm_engine}}, {{safety_taxonomy}}, {{prompt_enrichment_tools}}, {{image_resolution_constraints}}, {{retry_policy}}, {{downstream_generator}}) appear correctly in the brief.
  • Ensure safety evaluation occurs before parameter formatting.
  • Validate that no manual human review steps are introduced into the autonomous loop.
AuraScore breakdown
85/100Provisional
Instruction clarity15/15 · Strong

Explicit role, a named task, and discrete steps the model can follow.

Context architecture12/12 · Strong

Background, inputs and variables the model needs before it starts.

Constraint engineering8/12 · Adequate

Hard boundaries — what the model must and must not do.

Output specification14/14 · Strong

A named, field-level shape for the response.

Reasoning structure10/10 · Strong

Ordered work items that force analysis before an answer.

Model compatibility10/10 · Strong

Length and structure that travel across frontier models.

Token efficiency5/10 · Thin

Signal density — instruction weight without padding.

Reusability7/7 · Strong

Documented variables so the scaffold adapts to new inputs.

Robustness3/5 · Adequate

Quality bar, assumptions and behaviour when inputs are thin.

Observed performance1/5 · Thin

How much real usage the template has behind it.

ai-agents
agents-tool-calling
image-multimodal-prompting
prompt-engineering
safety-filtering
vlm