Skip to main content
Glama
蓝汐 · 潮汐认知图谱

蓝汐 · 潮汐认知图谱

by A16Nights

cg_reflect

Record metacognitive reflections or unresolved questions in self or unresolved layers, linking each entry to supporting evidence nodes for traceable memory updates.

Instructions

记录元认知反思或待解决问题(写入 self 或 unresolved 层,并关联 derived_from 依据节点)。

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": {
      "content": "<content>"
    },
    "name": "cg_reflect"
  }
}

Input Schema

NameRequiredDescriptionDefault
tagsNo
layerNo默认 self
titleNo
contentYes反思结论或待解决疑问
basedOnIdsNo关联依据节点 ID 列表
importanceNo默认 0.75

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

B3.1/5.0
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 does not state whether records are created or merged, whether duplicates are deduplicated, what permissions or preconditions apply, or what is returned. The note that entries are written into the self/unresolved layer and linked as derived_from is useful, but it is largely a restatement of the layer and basedOnIds fields.

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?

One compact sentence with the action front-loaded and the qualifying detail in a trailing parenthetical. There is no filler, though the parenthetical packs two distinct facts (layer target and provenance linking) without separating them.

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?

For a six-parameter mutation tool with no annotations and no output schema, the description is thin: it omits the effect of importance, the role of tags and title, duplicate/merge behavior, and any hint of how the record is later retrieved. An agent could invoke it, but not confidently or correctly in edge cases.

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 67%, so the baseline is a 3. The description does add one piece of genuine meaning by mapping basedOnIds to derived_from evidence links, which the schema field text does not say. It says nothing about tags, title, or the meaning/effect of the importance value.

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?

States a specific verb and resource: recording metacognitive reflections or unresolved questions, and names the two target layers (self / unresolved). An agent can distinguish this from a generic memory write. It does not, however, contrast itself with siblings like cg_write or cg_goal, so the differentiation is implicit rather than explicit.

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?

"记录元认知反思或待解决问题" implies the usage context (post-task reflection, open questions) but gives no when-to-use/when-not guidance and never names an alternative tool such as the general write or goal tools. The agent must infer that this is the reflection-specific path.

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