Skip to main content
Glama

AceRound AI Interview Copilot

save_custom_prompt

Save the full custom prompt from the prompt studio: when non-empty it replaces the built-in instructions for interview answers or exam answers; an empty string goes back to the built-in style plus extra requirements. baseline records which official text this prompt was derived from for future official-update merges: if you started from a text in get_prompt_presets pass that one (official / current / style:), after a sync rewrite pass official, for a prompt written from scratch pass none, and omit it for small edits to keep the existing record. (Requires the user's sign-in with scope interviews:write.)

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": {
      "scene": "<scene>",
      "prompt": "<prompt>"
    },
    "name": "save_custom_prompt"
  }
}

Input Schema

NameRequiredDescriptionDefault
langNoInterview language this prompt is for; defaults to the saved one
sceneYesinterview answers / exam answers
promptYesFull prompt; empty string = stop customizing
baselineNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations only cover the safety triad (readOnly=false, destructive=false, openWorld=false); the description adds real behavior beyond that: the save overwrites built-in instructions, an empty prompt reverts to built-in style plus extra requirements, and baseline is retained across future official-update merges (and preserved when omitted). It also discloses the required sign-in scope (interviews:write), which is exactly the kind of auth context annotations cannot express.

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 main action and its replace/reset semantics are front-loaded in the first sentence, with baseline derivation guidance following. The baseline sentence is long and colon-chained, but each clause (which value in which situation) carries information the agent needs and could not infer from the enum.

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?

For a 4-parameter mutation tool with no output schema, the definition covers purpose, reset semantics, baseline provenance, and the auth scope requirement — enough to call it correctly. Remaining gaps are minor: how language selection interacts with the saved prompt when lang is omitted is only covered by the schema text, and no return/confirmation behavior is described (largely acceptable since write tools typically return the saved record).

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?

Schema coverage is 75%, and the one undocumented-looking parameter, baseline, is fully explained in the description — including the official/current/style:<value>/none vocabulary and the omit-for-small-edits rule — which adds meaning the enum alone does not convey. The prompt parameter also gains semantics (empty string = stop customizing) beyond its schema text. Only lang is left to the schema, so it falls just short of full compensation.

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 ("Save the full custom prompt from the prompt studio") and immediately spells out the two outcome modes: non-empty replaces the built-in instructions for interview/exam answers, empty string reverts to the built-in style plus extra requirements. It also names the sibling get_prompt_presets as the source of baselines, so the agent can distinguish this write tool from preset-listing and rewriting tools.

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

Usage Guidelines4/5

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

Gives conditional guidance on the key decision the agent must make: what to pass for baseline depending on derivation path (started from a get_prompt_presets text, after a sync rewrite, from scratch, or small edit). It also clarifies the empty-string case as the way to stop customizing. It does not explicitly contrast this tool with rewrite_prompt or run_prompt_trial, so no exclusions are stated.

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