Skip to main content
Glama

run_prompt_completion

Executes prompt templates against the configured model and returns completion text plus requested tool calls or function calls as data—never executing them.

Instructions

Execute a prompt against the configured model and return the completion text, plus any tool_calls or function_call the model requested (returned as data, never executed). This makes a billable model call, so use render_prompt first when you want to check the template and validate_completion_metadata when billing fields are uncertain.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "prompt_id": "<prompt_id>",
      "variables": "<variables>",
      "metadata": "<metadata>"
    },
    "name": "run_prompt_completion"
  }
}

Input Schema

NameRequiredDescriptionDefault
metadataYesBilling metadata - client_id, app, env are REQUIRED for cost attribution
prompt_idYesPrompt ID or slug to execute
variablesYesVariable values to substitute into the template
hyperparametersNoOverride default hyperparameters

Output Schema

NameRequiredDescriptionDefault
okYesCall succeeded
dataNoSuccess payload
errorNoFailure details

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changedv0.16.5
    • changedOutput schema / properties / data / description
      Previous value: -"Structured success payload when ok is true"New value: +"Success payload"
    • changedOutput schema / properties / error / description
      Previous value: -"Structured error payload when ok is false"New value: +"Failure details"
    • changedOutput schema / properties / error / properties / details / description
      Previous value: -"Optional structured error details"New value: +"Extra error details"
    • changedOutput schema / properties / error / properties / message / description
      Previous value: -"Human-readable error message"New value: +"Error message"
    • changedOutput schema / properties / ok / description
      Previous value: -"Whether the tool call succeeded and returned structured data"New value: +"Call succeeded"
  2. Changed2 schema fields changedv1.0.9
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
    • changedOutput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
  3. Changed2 schema fields changedv0.12.2
    • removedInput schema / properties / variables / additionalProperties / anyOf
      Removed value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "number"
      -  },
      -  {
      -    "type": "boolean"
      -  }
      -]
    • addedInput schema / properties / variables / additionalProperties / type
      Added value: +[
      +  "string",
      +  "number",
      +  "boolean"
      +]
  4. Addedv1.0.1
  5. Removed
  6. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already disclose readOnlyHint=false, openWorldHint=true and destructiveHint=false, but the description adds two things they do not: the call is billable, and any tool_calls/function_call are returned as data and never executed. That second point is critical and non-obvious. It stops short of covering failure modes, rate limits, or whether repeated calls are charged differently, so not a 5.

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

Conciseness5/5

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

Two sentences with zero filler, front-loaded on what the tool does and what it returns, followed by cost and routing guidance. Every clause carries information an agent needs before calling.

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

Completeness4/5

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

An output schema exists, so return-shape explanation is correctly omitted, and the description covers cost and the non-execution of returned tool calls. For a 4-parameter nested-object mutation-adjacent call, it could still say what happens when required variables are missing, but nothing essential to calling correctly is absent.

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%, with prompt_id, variables, metadata and hyperparameters all documented in-schema including required billing fields. The description adds no parameter-level meaning beyond that, so the baseline 3 applies; it neither compensates for nor creates a gap.

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

Purpose5/5

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

States a specific verb-and-resource pair ('Execute a prompt against the configured model') and names exactly what comes back: completion text plus any tool_calls or function_call. It is also distinguishable from the sibling reading tools, which only manage prompt templates rather than running inference.

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

Usage Guidelines5/5

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

Explicitly routes the agent to alternatives with conditions: render_prompt 'when you want to check the template' and validate_completion_metadata 'when billing fields are uncertain'. The cost trigger ('billable model call') gives a clear reason to prefer those alternatives when appropriate.

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

Deploy Server

Other Tools