Skip to main content
Glama
Sign In
Claudegram

Claudegram

by sanjar-x
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

summarize_chat

Read-onlyIdempotent

Summarize recent chat messages by retrieving the last N messages and generating a client-side LLM summary. Optionally pass custom instructions to tailor the summary format.

Instructions

Резюме последних N сообщений чата через LLM-вызов клиента.

Args: chat: id или @username. limit: 1-200 сообщений. instruction: дополнительная инструкция для модели (например, "сделай маркированный список", "выдели action items").

Если клиент не поддерживает sampling — возвращает сырые сообщения и просит юзера резюмировать самому.

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": {
      "chat": "<chat>"
    },
    "name": "summarize_chat"
  }
}

Input Schema

NameRequiredDescriptionDefault
chatYes
limitNo
instructionNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.0

TDQS

A4.6/5.0
Behavior4/5

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

The annotations already mark the operation as read-only, open-world, idempotent, and non-destructive. The description adds context by stating it invokes the client's LLM and, if sampling is unsupported, returns raw messages and asks the user to summarize. No contradiction exists.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description consists of a one-line summary, a short structured Args block, and a conditional note about unsupported sampling. Each element is necessary and compact, with the main purpose front-loaded.

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?

Given the presence of an output schema and safe-read annotations, the description provides enough operational detail: purpose, parameter semantics, and fallback behavior. It covers the tool's core functionality without unnecessary elaboration, making it complete for an agent to select and invoke.

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 descriptions cover 0% of parameters, so the description's 'Args' section is essential. It explains chat as 'id или @username,' limit as '1-200 сообщений,' and instruction with concrete examples like 'сделай маркированный список' and 'выдели action items,' adding meaning beyond the bare schema types.

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?

The description opens with 'Резюме последних N сообщений чата через LLM-вызов клиента,' which clearly identifies the function as summarizing the last N chat messages using an LLM call. This is a specific verb+resource+scope that distinguishes it from sibling tools like get_history or search_messages.

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?

The description implies usage for any need to get a concise summary of recent conversation, and the fallback note ('Если клиент не поддерживает sampling — возвращает сырые сообщения') sets expectations when the client lacks sampling support. However, it doesn't explicitly name alternative tools or exclusion conditions, so it's a clear context without full guidance.

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

Deploy Server

Other Tools