agent-memory-router

read_raw_data

Retrieve the full original text of a single memory record by its ID, optionally limiting output with max_chars. Use it after search identifies a specific record, not to browse history.

Instructions

按记录 ID 读取单条记忆的完整原文。

只能对 search_memory 已经定位到的具体 ID 调用。 不要用它来遍历历史 —— 那正好是本系统要避免的行为。

Args: record_id: 记录 ID，形如 D_0001。 max_chars: 可选。>0 时只返回前 N 个字符（长文先看开头再决定）。

Returns: JSON：{ok, id, type, title, content, size_bytes, truncated, relations}

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": {
      "record_id": "<record_id>"
    },
    "name": "read_raw_data"
  }
}

Input Schema

Name	Required	Description	Default
`max_chars`	No
`record_id`	Yes

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.2.0Oct 31, 2026

TDQS

A4.7/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses the truncation behavior, the returned fields, and the anti-iteration design constraint. It does not mention permission/auth requirements, but for a read-only single-record fetch that is a minor gap; the output shape is also partly duplicated from the existing output schema.

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-loaded with the core action and the prohibition, then structured Args/Returns. Slightly redundant is the Returns block, since a full output schema already exists, but the rest of the text is tight and earns its place.

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

Completeness5/5

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

For a 2-param read tool with an output schema, the description covers purpose, precondition, exclusion, parameter formats, and truncation semantics — nothing an agent needs in order to call it correctly is missing.

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

Parameters5/5

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

Schema coverage is 0%, so the description must compensate, and it does: record_id is described with an example format (`D_0001`) and max_chars is given real semantics (only when >0, returns first N chars) plus the intent of previewing long documents before deciding.

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?

Names a specific verb (read) and resource (single record's full raw text) scoped to a record ID, and explicitly contrasts itself with the search path ('not for traversing history'). The sibling distinction from search_memory is stated in the description itself.

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

Usage Guidelines5/5

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

Explicitly states the precondition ('only call with a concrete ID already located by search_memory') and the exclusion ('do not use it to traverse history — that is exactly the behavior this system avoids'). An agent can route between this and search_memory without inference.

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

Deploy Server