Skip to main content
Glama

保存人物卡

app_save_persona

Create or update persona cards for Codex CLI or OpenAI-compatible APIs, including model, permissions, and memory settings; returns a sanitized structure.

Instructions

UI 专用:新增或编辑人物卡(支持 Codex CLI 与 OpenAI 兼容 API,返回脱敏结构)。

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": {
      "name": "<name>"
    },
    "name": "app_save_persona"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNo
nameYes
roleNo
modelNo
apiKeyNo
avatarNo
baseUrlNo
fastModeNo
memoriesNo
providerNo
toolModeNo
clearApiKeyNo
permissionsNo
systemPromptNo
addressUserAsNo
contextWindowNo
defaultSandboxNo
customCodexPathNo
reasoningEffortNo
cleanCodexConfigNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.1/5.0
Behavior3/5

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

No annotations are supplied, so the description carries the full behavioral burden. It does add one genuinely useful fact beyond the schema — the response is a sanitized structure ('返回脱敏结构'), so secrets like apiKey are not echoed back — but it omits persistence semantics, whether writes are immediate or reversible, and how apiKey/clearApiKey are handled server-side.

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?

A single compact sentence with the 'UI 专用' qualifier front-loaded and no filler. It is economical, though the economy comes partly at the cost of the detail the parameter surface demands.

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

Completeness2/5

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

With 20 parameters, a nested object, no annotations, and no output schema, the definition is far too thin to let an agent invoke it safely — especially the create-vs-update semantics implied by the optional id. The sanitized-return note is the only complexity-reducing detail provided.

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

Parameters2/5

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

Schema description coverage is 0% across 20 parameters, including a nested permissions object and four enums, so the description must compensate and largely fails to. Only the provider enum and the apiKey redaction are indirectly touched; fields like toolMode, reasoningEffort, defaultSandbox, clearApiKey, and memories receive no explanation anywhere.

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 names a specific verb pair and resource: '新增或编辑人物卡' (create or edit a persona card), plus the provider scope (Codex CLI and OpenAI-compatible API). It does not distinguish itself from sibling save tools such as app_save_default_permissions or app_save_user_profile beyond the resource noun, but the resource itself is unambiguous.

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

Usage Guidelines3/5

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

'UI 专用' is the only usage signal; it implies a restriction (this path is for the UI surface) but never states when an agent should prefer it, whether a non-UI alternative exists, or what preconditions apply. The agent is left to infer that create-vs-edit is selected by the presence of the optional id field.

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