Skip to main content
Glama
Arize-ai

@arizeai/phoenix-mcp

Official
by Arize-ai

get-latest-prompt

Retrieve the current version of a prompt with its template, model configuration, and invocation parameters for consistent AI interactions.

Instructions

Get the latest version of a prompt. Returns the prompt version with its template, model configuration, and invocation parameters.

Example usage: Get the latest version of a prompt named 'article-summarizer'

Expected return: Prompt version object with template and configuration. Example: { "description": "Initial version", "model_provider": "OPENAI", "model_name": "gpt-3.5-turbo", "template": { "type": "chat", "messages": [ { "role": "system", "content": "You are an expert summarizer. Create clear, concise bullet points highlighting the key information." }, { "role": "user", "content": "Please summarize the following {{topic}} article:

{{article}}" } ] }, "template_type": "CHAT", "template_format": "MUSTACHE", "invocation_parameters": { "type": "openai", "openai": {} }, "id": "promptversionid1234" }

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
prompt_identifierYes

Implementation Reference

  • The core handler function for the 'get-latest-prompt' tool. It uses the PhoenixClient to fetch the latest version of the specified prompt via the API endpoint "/v1/prompts/{prompt_identifier}/latest" and returns the response data as formatted JSON text.
    async ({ prompt_identifier }) => {
      const response = await client.GET(
        "/v1/prompts/{prompt_identifier}/latest",
        {
          params: {
            path: {
              prompt_identifier,
            },
          },
        }
      );
      return {
        content: [
          {
            type: "text",
            text: JSON.stringify(response.data, null, 2),
          },
        ],
      };
    }
  • Registers the 'get-latest-prompt' tool on the MCP server, providing the name, description, input schema, and handler function.
      "get-latest-prompt",
      GET_LATEST_PROMPT_DESCRIPTION,
      getLatestPromptSchema.shape,
      async ({ prompt_identifier }) => {
        const response = await client.GET(
          "/v1/prompts/{prompt_identifier}/latest",
          {
            params: {
              path: {
                prompt_identifier,
              },
            },
          }
        );
        return {
          content: [
            {
              type: "text",
              text: JSON.stringify(response.data, null, 2),
            },
          ],
        };
      }
    );
  • Zod schema defining the input for the tool: requires a 'prompt_identifier' string (name or ID of the prompt).
    export const getLatestPromptSchema = z.object({
      prompt_identifier: z.string(),
    });
  • Calls the initialization function that registers the prompt tools, including 'get-latest-prompt', on the MCP server instance.
    initializePromptTools({ client, server });
Behavior3/5

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

With no annotations provided, the description carries full burden. It discloses that the tool returns a prompt version object with specific fields (template, model configuration, invocation parameters), which is helpful behavioral context. However, it doesn't mention whether this is a read-only operation, potential error conditions, authentication needs, or rate limits—important gaps for a tool with zero annotation coverage.

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

Conciseness3/5

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

The description is front-loaded with the core purpose, but the extensive example return object (15+ lines) dominates the text. While the example is informative, it could be summarized more concisely. The structure mixes description with implementation details, slightly reducing clarity.

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?

For a 1-parameter tool with no annotations and no output schema, the description provides adequate context on what the tool does and returns. However, it lacks information on error handling, authentication, and explicit differentiation from sibling tools. The example return object partially compensates for the missing output schema, but completeness is moderate given the tool's simplicity.

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

Parameters4/5

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

The input schema has 1 parameter with 0% description coverage, so the description must compensate. It provides an example showing 'prompt_identifier' should be a prompt name like 'article-summarizer', adding meaningful semantics beyond the schema's bare type declaration. However, it doesn't clarify format constraints (e.g., case sensitivity, allowed characters) or what happens if the prompt doesn't exist.

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 clearly states 'Get the latest version of a prompt' which is a specific verb+resource combination. It distinguishes from siblings like 'get-prompt-by-identifier' and 'get-prompt-version' by specifying 'latest version' rather than retrieving by specific identifier or version. However, it doesn't explicitly contrast with 'get-prompt-version-by-tag' which might also retrieve versions.

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

Usage Guidelines2/5

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

The description provides an example usage but offers no explicit guidance on when to use this tool versus alternatives like 'get-prompt-by-identifier' or 'get-prompt-version'. It doesn't mention prerequisites, exclusions, or comparative contexts with sibling tools, leaving the agent to infer usage from tool names alone.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Arize-ai/phoenix'

If you have feedback or need assistance with the MCP directory API, please join our Discord server