Skip to main content
Glama

Visibility Genies

Read saved prompt answers

get_saved_prompt_answers
Read-only

Reads the answers Prompt Explorer already bought for one prompt in this project: what the ChatGPT, Claude, Gemini and Perplexity APIs (and Grok, DeepSeek and Muse Spark, when asked) answered, with the sources they cited, and what the ChatGPT and Gemini apps show a person. Uses no credits and never buys: an answer that is not saved is named with the price a Run on Prompt Explorer asks for it, and ask_ai_models buys it at that price, as a Run does. For the same prompt answered again over time, get_tracked_prompts reads Prompt Tracking's runs.

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": {
      "projectId": "<projectId>",
      "prompt": "<prompt>"
    },
    "name": "get_saved_prompt_answers"
  }
}

Input Schema

NameRequiredDescriptionDefault
appsNoThe consumer apps whose answers to read. Defaults to none.
modelsNoThe API models whose answers to read. Defaults to the four, chat_gpt, claude, gemini and perplexity, as Prompt Explorer asks them; add grok, deepseek or muse_spark to read their saved answers too.
promptYesThe prompt, exactly as it was asked in Prompt Explorer.
countryNoThe country the answers were asked from. Defaults to the United States.
versionsNoThe version each API model was asked at, keyed by the model, as Prompt Explorer's picker names it. A model left out is read at the workspace's default version from Settings, else the built-in one.
projectIdYesRequired. The Visibility Genies project this call works in and is billed to. Call list_projects to find one.
webSearchNoWhether the API models were asked with web search. Defaults to true, as the page asks.

Output Schema

NameRequiredDescriptionDefault
metaNo
toBuyYes
answersYes
unreadableYes
toBuyPriceUsdYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • changedInput schema / properties / models / description
      Previous value: -"The API models whose answers to read. Defaults to the four, chat_gpt, claude, gemini and perplexity, as Prompt Explorer asks them; add grok to read its saved answers too."New value: +"The API models whose answers to read. Defaults to the four, chat_gpt, claude, gemini and perplexity, as Prompt Explorer asks them; add grok, deepseek or muse_spark to read their saved answers too."
    • changedInput schema / properties / models / items / enum
      Previous value: -[
      -  "chat_gpt",
      -  "claude",
      -  "gemini",
      -  "perplexity",
      -  "grok"
      -]New value: +[
      +  "chat_gpt",
      +  "claude",
      +  "gemini",
      +  "perplexity",
      +  "grok",
      +  "deepseek",
      +  "muse_spark"
      +]
    • changedInput schema / properties / models / maxItems
      Previous value: -5New value: +7
    • changedInput schema / properties / versions / propertyNames / enum
      Previous value: -[
      -  "chat_gpt",
      -  "claude",
      -  "gemini",
      -  "perplexity",
      -  "grok"
      -]New value: +[
      +  "chat_gpt",
      +  "claude",
      +  "gemini",
      +  "perplexity",
      +  "grok",
      +  "deepseek",
      +  "muse_spark"
      +]
  2. Changed4 schema fields changed
    • changedInput schema / properties / models / description
      Previous value: -"The API models whose answers to read. Defaults to all four, as Prompt Explorer asks them."New value: +"The API models whose answers to read. Defaults to the four, chat_gpt, claude, gemini and perplexity, as Prompt Explorer asks them; add grok to read its saved answers too."
    • changedInput schema / properties / models / items / enum
      Previous value: -[
      -  "chat_gpt",
      -  "claude",
      -  "gemini",
      -  "perplexity"
      -]New value: +[
      +  "chat_gpt",
      +  "claude",
      +  "gemini",
      +  "perplexity",
      +  "grok"
      +]
    • changedInput schema / properties / models / maxItems
      Previous value: -4New value: +5
    • changedInput schema / properties / versions / propertyNames / enum
      Previous value: -[
      -  "chat_gpt",
      -  "claude",
      -  "gemini",
      -  "perplexity"
      -]New value: +[
      +  "chat_gpt",
      +  "claude",
      +  "gemini",
      +  "perplexity",
      +  "grok"
      +]
  3. First observed

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, but the description adds the economically important fact that calls consume no credits and never trigger a purchase, plus the fallback behavior when an answer is not saved (the answer is named together with the price). It does not discuss rate limits or return shape, though the output schema covers the latter, so a 4 rather than 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.

Conciseness4/5

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

Purpose and cost semantics are front-loaded, and there is no filler. The second sentence is long and multi-clause (parenthetical model list plus price explanation plus alternative routing), which slightly hurts scanability for a definition this dense.

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

Completeness5/5

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

For a 7-parameter read with a nested versions object, full schema description coverage, annotations and an output schema, the description supplies the missing decision context: cost model, what happens for unsaved answers, and which siblings handle purchase and time-series cases. Nothing an agent needs to call this 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 coverage is 100% and the schema already documents defaults for models, apps, country and webSearch; the description's model list largely restates the enum. The only marginal addition is the implicit coupling of 'when asked' models to saved state, which the schema does not quite say, so baseline 3 applies.

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?

Opens with a specific verb and resource scoped to 'one prompt in this project' and enumerates exactly what is returned (API answers from ChatGPT/Claude/Gemini/Perplexity, optional Grok/DeepSeek/Muse Spark, cited sources, app views). This is clearly separable from ask_ai_models (buys) and get_tracked_prompts (tracking over time), both named in the text.

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 frames this as the free, no-purchase path ('Uses no credits and never buys') and names the alternative for the buying case ('ask_ai_models buys it at that price, as a Run does'). It also routes the repeat-over-time case to get_tracked_prompts, giving a when/when-not/alternative triad.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources