Skip to main content
Glama
verivus-oss

llm-cli-gateway

by verivus-oss
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

llm_job_result

Read-onlyIdempotent

Retrieve captured stdout and stderr for gateway async or deferred-sync jobs using a job ID. Supports resumable stream offsets for paging through large outputs.

Instructions

Retrieve captured stdout/stderr for a gateway async or deferred-sync job by jobId. Use rawOutput:true with independent stream offsets for resumable pages.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
jobIdYesAsync job ID from *_request_async
maxCharsNoMaximum chars returned per stdout/stderr page
rawOutputNoReturn captured provider streams without display parsing or compression. Available only to local stdio callers. Required for resumable offsets.
stderrOffsetCharsNoCaptured stderr character offset for resumable retrieval. Non-zero offsets require rawOutput:true.
stdoutOffsetCharsNoCaptured stdout character offset for resumable retrieval. Non-zero offsets require rawOutput:true.
nativeTranscriptOffsetCharsNoProvider-native transcript character offset for resumable retrieval. Non-zero offsets require rawOutput:true.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv3.2.0
    • addedInput schema / properties / nativeTranscriptOffsetChars
      Added value: +{
+  "default": 0,
+  "description": "Provider-native transcript character offset for resumable retrieval. Non-zero offsets require rawOutput:true.",
+  "minimum": 0,
+  "type": "integer"
+}
    • changedInput schema / properties / rawOutput / description
      Previous value: -"Return captured provider streams without display parsing or compression. Local stdio pages concatenate to the captured streams; remote pages redact provider session IDs. Required for resumable offsets."New value: +"Return captured provider streams without display parsing or compression. Available only to local stdio callers. Required for resumable offsets."
  2. Changed4 schema fields changedv3.0.0
    • changedInput schema / properties / maxChars / description
      Previous value: -"Max chars returned per stream"New value: +"Maximum chars returned per stdout/stderr page"
    • addedInput schema / properties / rawOutput
      Added value: +{
+  "default": false,
+  "description": "Return captured provider streams without display parsing or compression. Local stdio pages concatenate to the captured streams; remote pages redact provider session IDs. Required for resumable offsets.",
+  "type": "boolean"
+}
    • addedInput schema / properties / stderrOffsetChars
      Added value: +{
+  "default": 0,
+  "description": "Captured stderr character offset for resumable retrieval. Non-zero offsets require rawOutput:true.",
+  "minimum": 0,
+  "type": "integer"
+}
    • addedInput schema / properties / stdoutOffsetChars
      Added value: +{
+  "default": 0,
+  "description": "Captured stdout character offset for resumable retrieval. Non-zero offsets require rawOutput:true.",
+  "minimum": 0,
+  "type": "integer"
+}
  3. First observedv2.16.0

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the bar is low. The description adds behavioral context beyond those annotations: the tool serves both async and deferred-sync jobs and supports independent per-stream offset resumption across pages. No contradiction with the annotations.

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?

Two sentences with zero waste: the first states the purpose, the second states the critical usage mode. The most important operational detail (rawOutput:true for resumable offsets) is front-loaded right after the purpose statement.

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

Completeness3/5

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

For a read-only tool with rich annotations (four hints) and fully documented parameters, the description is mostly sufficient, and the return content is reasonably hinted by 'captured stdout/stderr'. However, with no output schema and a sibling list containing near-duplicates (llm_request_result, job_result), the absence of disambiguation or return-structure guidance leaves the definition incomplete.

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 each of the six parameters is thoroughly documented in the schema itself, including the rawOutput:true prerequisite for non-zero offsets. The description adds only a thin conceptual framing — linking rawOutput and offsets to 'resumable pages' — which is helpful context but not new parameter-level meaning. Baseline 3 is appropriate.

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?

The description names a specific verb ('Retrieve'), a precise resource ('captured stdout/stderr for a gateway async or deferred-sync job'), and the key selector (jobId). It reads distinctly from status/watch/cancel siblings, but never explicitly disambiguates from the near-identical llm_request_result and job_result tools that appear in the sibling list.

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?

There is clear in-tool guidance — 'Use rawOutput:true with independent stream offsets for resumable pages' — which tells the agent how to invoke the resumable mode. However, nothing states when to select this tool over close siblings like llm_request_result, job_result, or llm_job_status, which is a significant gap given the large sibling set.

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