Skip to main content
Glama

oc_last

Fetches the latest assistant reply and voice metadata from an agent's recent session messages to recover context after a lost run ID or bridge restart.

Instructions

读取指定 agent 的 glasses 会话最近 limit 条消息(默认 10,最大 50),返回最后一条 assistant 回复和 voice 播报元数据。用于 runId 丢失、桥接进程重启、或需要确认“刚才那个任务”说了什么。只播报最后一条 assistant 的内容概要,不要把历史逐条读出来。它只反映历史,不代表任务当前是否在运行——查状态请用 oc_wait;手上没有 runId 时也不要据此断言“还在跑”或“已完成”。

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "oc_last"
  }
}

Input Schema

NameRequiredDescriptionDefault
agentNoAgent 名字或 ID(先用 oc_agents 获取本机可用值)。留空使用默认 agent。
limitNo返回消息条数,默认 10,最大 50。

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.4/5.0
Behavior4/5

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

No annotations are supplied, so the description carries the full disclosure burden, and it does substantial work: output shape (last assistant reply + voice metadata), the 10/50 bounds, the fact that it is a historical snapshot rather than a live status signal, and an instruction to summarize only the last assistant message instead of replaying history. It does not cover permissions, error behavior, or what happens when the session has no messages, so it falls short of a 5 for an unannotated tool.

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?

It is front-loaded with the operation, then usage conditions, then the caveat, which is the right order for an agent scanning for eligibility. The only waste is the partial repetition of the 'history, not live status' caveat, which appears once as a statement and again as a warning against asserting running/completed.

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?

There is no output schema, and the description compensates by naming what comes back (last assistant reply plus voice metadata). For a two-parameter read tool with no annotations, it covers purpose, trigger conditions, the alternative, and the key misinterpretation risk, leaving nothing an agent needs in order to call it correctly.

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 description coverage is 100%, and the description largely restates what the schema already documents: the default of 10 and the maximum of 50 for `limit`. It adds no syntax, format, or edge-case meaning for `agent` beyond the schema's own pointer to oc_agents, so the baseline 3 applies.

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 states a specific verb and resource: read the last `limit` messages from a named agent's glasses session, and it states the return payload (last assistant reply plus voice broadcast metadata). It explicitly distinguishes itself from oc_wait by declaring it reflects history only, not live task status, so an agent can separate the two without opening a schema.

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?

It names concrete triggering situations (lost runId, bridge process restart, confirming what 'that task just now' said) and names the alternative for the status question: use oc_wait. It also gives an explicit prohibition against inferring 'still running' or 'completed' without a runId, which is the exact misuse this tool invites.

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