Skip to main content
Glama
runapi-ai

@runapi.ai/gemini-omni-mcp

by runapi-ai

create_character

Run a synchronous Gemini Omni operation on RunAPI (create character). Returns the operation result.

Instructions

Run a synchronous Gemini Omni operation on RunAPI (create character). Returns the operation result.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modelNoRunAPI model slug for this model line.
audio_idsNoAudio preset IDs returned by create-audio.
descriptionsYesCharacter appearance, identity, style, clothing, or personality description.
character_nameNoCharacter display name.
reference_image_urlYesPublic portrait reference image URL.
body_reference_image_urlNoOptional public full-body reference image URL; reference_image_url must provide the portrait.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.2.2
    • addedInput schema / properties / body_reference_image_url
      Added value: +{
      +  "description": "Optional public full-body reference image URL; reference_image_url must provide the portrait.",
      +  "type": "string"
      +}
    • changedInput schema / properties / reference_image_url / description
      Previous value: -"Public character reference image URL."New value: +"Public portrait reference image URL."
  2. Changed6 schema fields changedv0.2.1
    • addedInput schema / properties / audio_ids / description
      Added value: +"Audio preset IDs returned by create-audio."
    • addedInput schema / properties / character_name / description
      Added value: +"Character display name."
    • addedInput schema / properties / character_name / maxLength
      Added value: +210
    • addedInput schema / properties / descriptions / description
      Added value: +"Character appearance, identity, style, clothing, or personality description."
    • addedInput schema / properties / descriptions / maxLength
      Added value: +20000
    • addedInput schema / properties / reference_image_url / description
      Added value: +"Public character reference image URL."
  3. Changed8 schema fields changedv0.2.0
    • addedInput schema / properties / audio_ids
      Added value: +{
      +  "items": {},
      +  "type": "array"
      +}
    • addedInput schema / properties / character_name
      Added value: +{
      +  "type": "string"
      +}
    • addedInput schema / properties / descriptions / type
      Added value: +"string"
    • removedInput schema / properties / poll_interval_ms
      Removed value: -{
      -  "exclusiveMinimum": 0,
      -  "type": "integer"
      -}
    • addedInput schema / properties / reference_image_url / type
      Added value: +"string"
    • removedInput schema / properties / timeout_ms
      Removed value: -{
      -  "exclusiveMinimum": 0,
      -  "type": "integer"
      -}
    • removedInput schema / properties / wait
      Removed value: -{
      -  "default": true,
      -  "description": "Poll until the task reaches a terminal status.",
      -  "type": "boolean"
      -}
    • addedInput schema / required
      Added value: +[
      +  "descriptions",
      +  "reference_image_url"
      +]
  4. First observedv0.1.0

TDQS

B3.2/5.0
Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the operation is 'synchronous' and 'returns the operation result', which is useful, but it does not disclose side effects, cost implications, rate limits, or what happens on failure. For a tool that likely creates a resource and may incur charges, this is a significant gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that is concise and front-loaded with the key action ('Run a synchronous Gemini Omni operation'). It wastes no words, though it could add a bit more context without becoming verbose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has 6 parameters, no output schema, and no annotations, the description is somewhat thin. It tells the agent the operation is synchronous and returns a result, but it does not explain the relationship between audio_ids and create-audio, the need for a public URL, or what the result contains. The schema covers parameters, but the description does not fully compensate for the lack of annotations and output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all six parameters. The description adds no additional parameter-level meaning beyond the schema. Baseline 3 is appropriate because the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('Run'), a resource ('Gemini Omni operation on RunAPI'), and the operation's purpose ('create character'). It is clear about what the tool does, though it does not explicitly differentiate it from sibling tools like create_audio or text_to_video beyond the 'create character' phrase.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage by naming the operation ('create character') and the platform (RunAPI), but it does not explicitly state when to use this tool versus alternatives like create_audio or text_to_video. The schema provides required parameters (descriptions, reference_image_url) which hint at prerequisites, but no explicit when/when-not guidance is given.

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