Skip to main content
Glama

面灵AI 面试助手

save_custom_prompt

保存提示词工作台中的整段自定义提示词:非空时整段取代内置写法(面试作答或笔试答题);传空串即恢复按内置风格与额外要求作答。baseline 记录这段由哪份官方原文改来,供日后「同步官方更新」比对:以 get_prompt_presets 的某一段为底稿修改时传对应值(official / current / style:<档位>),sync 改写后传 official,从零手写传 none,只做小修改不传(保持原记录)。(需要用户授权,范围 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
langNo这段提示词对应的面试语言;不传按用户已保存的面试语言
sceneYesinterview 面试作答 / exam 笔试答题
promptYes整段提示词;空串 = 不再自定义
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 declare readOnlyHint=false / destructiveHint=false / openWorldHint=false; the description goes further by disclosing that a save overwrites the entire built-in prompt and that an empty string is a destructive-to-customization reset, and it states the authorization requirement (interviews:write) and the provenance-tracking purpose of baseline. It does not state what happens to prior baseline records on a partial save beyond '保持原记录', but coverage is well above the annotation baseline.

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?

Front-loads the save/reset semantics in the first sentence and confines provenance detail to the second; every clause carries information. The single dense block with parenthetical value lists is harder to scan than a bulleted structure would be, but nothing is redundant.

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 write tool with annotations and no output schema, the definition covers replacement semantics, the reset case, per-value baseline guidance, and the permission scope. It omits any note on size limits (the 20,000-char cap lives only in the schema) and on what a successful save returns or invalidates.

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 undocumented parameter is exactly baseline, whose enum values the description explains one by one (official / current / style:<档位> / none / omit). The distinction between 'official' and 'current' remains slightly implicit, so it adds strong but not complete meaning beyond the schema.

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 ('保存…整段自定义提示词') and pins down the effect precisely: a non-empty value wholesale replaces the built-in writing (interview or exam), an empty string restores the built-in style. An agent can immediately distinguish this from read-only siblings like get_prompt_presets.

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 concrete conditional guidance for the baseline field (edit from a get_prompt_presets segment = pass that value; after sync rewrite = 'official'; hand-written from scratch = 'none'; minor edit = omit to keep the record), plus the empty-string reset path. It lacks explicit guidance on when to choose this over the related rewrite_prompt or run_prompt_trial siblings, so it falls short of a 5.

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