Skip to main content
Glama

save_card

Saves locked character, goldfinger, tone, and hard-data cards to a project so novel constraints and drift checks stay consistent.

Instructions

【锁定层】保存人设卡/金手指卡/调性对照卡/硬数据。

  • character:必须给 forbidden 禁止项数组(≥5 条,否定式定义法)与 drift_signals 漂移预警信号;肯定项 traits 控制在 3-5 个。

  • goldfinger:必须给 boundaries 边界数组(边界 > 能力);建议 legs 三条腿(各含 name/limit)。

  • tone:is(本项目是什么)+ isNot(对立面)+ dimensions 对照表 [{dimension, self, opposite}](对立面定义法)。

  • harddata:entries [{key, value}] 硬数据校验表(年龄/姓名/关键数字/时间线)。

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": {
      "project_id": "<project_id>",
      "card_type": "<card_type>",
      "payload": "<payload>"
    },
    "name": "save_card"
  }
}

Input Schema

NameRequiredDescriptionDefault
payloadYes卡内容,结构见工具描述
card_typeYes
project_idYes项目 ID(内部代号,如“默者”)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

B3.3/5.0
Behavior2/5

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, yet it never discloses write semantics: whether saving overwrites or appends an existing card of the same type, whether an under-specified payload is rejected or silently stored, or what the tool returns. Calling these cards a 'lock layer' hints at authority, but that hint is never turned into a stated effect.

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 front-loaded purpose sentence followed by four parallel bullets keyed to the enum values; no filler and easy to scan. Density is high but earned, with only minor abbreviations (is/isNot, legs) that assume domain familiarity.

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 three-parameter mutation with a nested free-form payload, the description usefully documents payload shape per card type, which is the main risk area. Missing is the write contract: return value, overwrite or append behavior, and validation failure handling, none of which is covered by annotations or an output schema.

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 description coverage is only 67%, and the schema's payload field defers entirely to the description ('结构见工具描述'). The bullets fill that gap by specifying per card_type the required sub-structures: a forbidden array with at least 5 negations plus drift_signals for character, a boundaries array for goldfinger, an is/isNot/dimensions table for tone, and key/value entries for harddata. This is real meaning added beyond the schema, though it stops at the mandatory minimum and leaves optional fields unlisted.

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 opening line uses a specific verb plus an enumerated resource set: 保存 saves 人设卡/金手指卡/调性对照卡/硬数据 (character, goldfinger, tone, hard-data cards), and the per-type bullets match the card_type enum exactly, so an agent can tell what each mode stores. There is no explicit differentiation from siblings such as save_outline, but the scope 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?

The 【锁定层】 (lock layer) tag implies a project phase and the bullets state mandatory content per card type, which is de facto 'how to use it correctly'. It never says when to choose a card instead of save_outline or init_project, nor whether a type may be saved more than once, so usage is implied rather than stated.

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