Skip to main content
Glama

Read one persisted task record and stage result (read-only, bounded)

dsh_get_history
Read-onlyIdempotent

Reads one recorded task or stage from persisted bridge history to review read-only task, checkpoint, and delivery evidence; missing or corrupt stage results are reported explicitly.

Instructions

Reads one task recorded by an earlier bridge process, optionally one stage. Returns a fixed read-only envelope (source=persisted-history, runtimeAttached=false, runtimeAlive=null, canContinue=false, canCancel=false) plus projected, scrubbed task/stage/checkpoint/delivery evidence. Prompts, context, environment, reasoning, raw argv and record-controlled absolute paths are not returned. A missing or corrupt stage result is reported explicitly and never replaced with an earlier stage. The recorded PID is never probed or used for process control.

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": {
      "taskId": "<taskId>"
    },
    "name": "dsh_get_history"
  }
}

Input Schema

NameRequiredDescriptionDefault
stageNoRecorded stage number. Defaults to the latest recorded stage.
taskIdYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.8

TDQS

A3.9/5.0
Behavior5/5

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

Annotations already declare readOnlyHint/idempotentHint/non-destructive, but the description adds substantial context beyond them: the exact fixed envelope fields and their values, what is deliberately scrubbed from results, that a missing or corrupt stage is reported explicitly rather than backfilled, and that the recorded PID is never probed. These are precisely the behavioral facts an agent needs before relying on the output.

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 verb and resource, then the return contract, then the exclusions and failure semantics. Dense but nearly every clause carries information; the parenthetical envelope enumeration is the only heavy passage, and it is justified because no output schema exists.

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 takes on the return-value burden and does so well by enumerating envelope fields, scrubbing rules, and error behavior. It stops short of explaining how to discover a valid taskId or how this relates to listing/history siblings, which an agent would still need to infer.

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 50%: 'stage' is documented in the schema, including its default to the latest recorded stage, which the description only echoes. 'taskId' carries no schema description and the description does not describe its format or where to source it, so no real meaning is added beyond the structured fields.

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 ('Reads one task recorded by an earlier bridge process, optionally one stage') plus the scope of the persisted-history envelope. It implicitly separates itself from live-task siblings by emphasizing 'recorded by an earlier bridge process' and runtimeAttached=false, but never names a counterpart, so differentiation is inferred rather than stated.

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?

The description establishes a clear context (reading persisted records from a prior process, as opposed to anything live) and clarifies that the stage argument is optional. It never states when to prefer this over dsh_get_task, dsh_get_result or dsh_list_history, and gives no prerequisite such as how a taskId is obtained, leaving selection to inference.

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