Skip to main content
Glama

jobd_logs

Read-only

Read the captured stdout/stderr tail of a running or finished job to check progress, diagnose failures from tracebacks, or retrieve final output.

Instructions

Tail the captured stdout/stderr of a job (workers stream output to the broker's per-job log as it runs). Returns log_tail (last tail_bytes, default 8 KiB, max 1 MiB) plus size_bytes/returned_bytes/truncated — works for running AND finished jobs. Use to check progress mid-run, diagnose a failure's traceback, or grab a job's final output.

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": {
      "job_id": "<job_id>"
    },
    "name": "jobd_logs"
  }
}

Input Schema

NameRequiredDescriptionDefault
job_idYesNumeric job id whose captured output to read.
tail_bytesNoHow many bytes from the END of the log to return (server caps reads at 1 MiB). Raise for context, lower for a quick liveness peek.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.5.47
    • addedInput schema / additionalProperties
      Added value: +false
  2. Addedv0.5.35
  3. Removedv0.5.34
  4. Changed2 schema fields changed
    • addedInput schema / properties / job_id / description
      Added value: +"Numeric job id whose captured output to read."
    • addedInput schema / properties / tail_bytes / description
      Added value: +"How many bytes from the END of the log to return (server caps reads at 1 MiB). Raise for context, lower for a quick liveness peek."
  5. First observedv0.5.5

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered; the description adds materially by disclosing the byte cap (max 1 MiB read), the default 8 KiB tail, truncation via a 'truncated' flag, and that output is incrementally streamed to the broker while the job runs. The 'from the END of the log' semantics and the freshness implication are exactly the kind of behavior annotations cannot express.

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 core action, then mechanism in parentheses, then return shape, then usage — a logical progression with no filler sentences. The only waste is the mild duplication of 'default 8 KiB, max 1 MiB', which the parameter schema already states.

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 usefully enumerates the return fields (log_tail, size_bytes, returned_bytes, truncated) and the truncation condition, so an agent knows what to expect. Combined with the running/finished scope and read cap, nothing essential for correct invocation is missing, though encoding/ordering of tailed lines is unstated.

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%, so both parameters already carry descriptions, defaults, and the 1 MiB maximum. The description restates the default and cap without adding new syntax or constraints beyond what the schema says; baseline 3 applies when the schema does the heavy lifting.

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 pairs a specific verb ('Tail') with a specific resource ('captured stdout/stderr of a job') and explains the mechanism by which that output exists (workers stream to the broker's per-job log). The stdout/stderr framing implicitly separates it from event- or status-oriented siblings, but no sibling is named, so it stops short of the top score.

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?

It gives three concrete use cases: checking progress mid-run, diagnosing a failure's traceback, and grabbing final output, plus the important scope note that it works for running AND finished jobs. There is no explicit when-not guidance or named alternative (e.g., use jobd_events for lifecycle events), which keeps it at 4.

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