Skip to main content
Glama

Read one stage result: model report and bridge-observed evidence (read-only)

dsh_get_result
Read-onlyIdempotent

Retrieve the latest or a named stage result for a delegated task, including the model report, bridge-recorded evidence, verification status, and a compact delivery summary with evidence paths.

Instructions

Returns the latest or a named stage. Model report and bridge evidence are separate. modelReport.previewTruncated means only the display preview was shortened; upstreamTruncated means the model hit its output limit and the stage is incomplete. Full recorded text stays on disk. bridgeObserved.toolCallsTotal is the TRUE tool-call total (not the retained 60); usageAccounting separates latest, stage sum and task sum (missing counters are null, never 0); verification.status states whether the bridge command ran, its attempts/exit code and any not-run reason; deliverySummary gives a compact deterministic acceptance basis and evidence paths. Model-internal reasoning is excluded.

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_result"
  }
}

Input Schema

NameRequiredDescriptionDefault
stageNoStage number. Defaults to the latest stage.
taskIdYes
verboseNoInclude up to 60 tool observations instead of 25.

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?

Goes well beyond the readOnly/idempotent annotations: it explains that model-internal reasoning is excluded, that full recorded text stays on disk, and that the two truncation flags mean different things (display preview vs. model hitting its output limit). It also discloses accounting conventions (missing counters are null, never 0) and the gap between true tool-call total and the retained subset, which an agent cannot discover from structured fields.

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?

Every sentence carries load — the field-semantics sentences are dense but not padded, and the lead sentence is front-loaded. It reads as a semicolon-separated run rather than a structured list, which slightly hurts scannability.

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 must carry return-value meaning, and it does so for the most error-prone fields: truncation, usage accounting, verification status, and delivery summary. It does not enumerate the full response shape, so an agent still has unknowns, but the critical interpretation traps are covered.

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 67%: stage and verbose are documented in the schema, taskId is not. The description reinforces stage defaulting to the latest and ties the retained 60 tool observations to the verbose parameter's upper bound, but adds nothing about taskId. Baseline 3 is appropriate given the schema does most of the work.

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?

Opens with a specific verb and resource: 'Returns the latest or a named stage', and the title clarifies it is the stage result with model report plus bridge-observed evidence. It does not explicitly differentiate from siblings such as dsh_get_task or dsh_get_events, so an agent must infer the boundary.

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?

Usage is implied by the resource ('read one stage result'), and the read-only nature is carried by annotations. There is no statement of when to prefer this over dsh_get_task or dsh_get_events, and no prerequisites such as the stage needing to exist.

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