Skip to main content
Glama

Read live output

dsh_read
Read-onlyIdempotent

Read a running conversation's output incrementally with a cursor, so you can monitor progress and partial results before the turn ends. Call repeatedly with the last cursor to track multiple conversations.

Instructions

Read a conversation's run-time output (cursor-based and incremental): see what a running conversation has produced so far without waiting for the turn to end. Typical use: dsh_list(only_running) to find active conversations, then call dsh_read repeatedly, passing back the last cursor, to watch several in turn. The output buffer is memory-only and bounded (a ring; the oldest entries are dropped) and disappears when the server or process exits. Reasoning is not buffered: live reasoning of the turn currently running is attached only with include_reasoning=true. The cursor is a revision number: an entry whose text grew is returned again; match it by seq and replace its text (do not append twice).

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": {
      "conversation_id": "<conversation_id>"
    },
    "name": "dsh_read"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMaximum entries per call. Default 200.
cursorNoThe cursor returned last time; omit or pass 0 on the first call.
conversation_idYesConversation id, from dsh_start or dsh_list.
include_reasoningNoAttach the live reasoning of the current turn. Default false.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv0.6.8
    • changedInput schema / properties / conversation_id / description
      Previous value: -"会话 id,来自 dsh_start 或 dsh_list。"New value: +"Conversation id, from dsh_start or dsh_list."
    • changedInput schema / properties / cursor / description
      Previous value: -"上次返回的 cursor;首次不传或传 0。"New value: +"The cursor returned last time; omit or pass 0 on the first call."
    • changedInput schema / properties / include_reasoning / description
      Previous value: -"附带当前回合的实时思考内容,默认 false。"New value: +"Attach the live reasoning of the current turn. Default false."
    • changedInput schema / properties / limit / description
      Previous value: -"单次最多返回多少条,默认 200。"New value: +"Maximum entries per call. Default 200."
  2. First observedv0.1.0

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, yet the description adds substantial context they cannot carry: the buffer is a memory-only bounded ring whose oldest entries are silently dropped, it vanishes on server or process exit, and live reasoning is only attached when include_reasoning=true. It also warns that entries can be returned again when text grows, which is critical behavior an agent would otherwise get wrong.

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 purpose, then workflow, then buffer lifetime, then cursor mechanics – a sensible information order with strong emphasis markers on the constraints that matter. It is dense and slightly long, but nearly every sentence carries operational content; only the `seq` de-duplication instruction edges toward implementation detail.

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

Completeness4/5

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

With no output schema, the description does well: it implicitly describes entries carrying `seq` and `text`, explains buffer boundness and disappearance, and covers the reasoning caveat. What remains unstated is the concrete response envelope (e.g. whether the next cursor is returned alongside entries), which the agent must discover by calling.

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 coverage is 100%, so baseline is 3, but the description genuinely enriches two parameters: cursor is explained as a revision number with the 'omit or 0 on first call' convention, and include_reasoning is tied to the fact that reasoning is not buffered. It says nothing about limit beyond what the schema already states, keeping it below a 5.

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?

States a specific verb and resource ('Read a conversation's run-time output') and immediately narrows the scope with 'cursor-based and incremental ... without waiting for the turn to end'. That scope clause distinguishes it from a sibling like dsh_get that presumably returns completed results, so an agent can tell them apart without opening either schema.

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?

Gives an explicit workflow: dsh_list(only_running) to find active conversations, then repeated dsh_read calls passing the prior cursor to watch several in turn. It does not explicitly state the negative case (e.g. that reading a completed or non-running conversation returns nothing and dsh_get should be used instead), so it stops short of full when/when-not guidance.

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