Skip to main content
Glama

job_feedback

Record your verdict on a delegated job to update acceptance statistics and pass a one-sentence lesson to the executor for future tasks in the same project.

Instructions

Your verdict on a delegated job. It feeds the acceptance statistics, and lesson (one sentence on what to do differently, or what was right) is given to the executor at its next tasks in the same project. For non-trivial changes, weak checks, or jobs with contract constraints, and for any job that had no check, accepted=True requires inspecting job_diff(job_id) first (and setting constraints_verified=True when constraints were provided).

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>",
      "accepted": "<accepted>"
    },
    "name": "job_feedback"
  }
}

Input Schema

NameRequiredDescriptionDefault
job_idYes
lessonNo
acceptedYes
constraints_verifiedNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv3.6.1
    • addedInput schema / properties / constraints_verified
      Added value: +{
      +  "default": false,
      +  "title": "Constraints Verified",
      +  "type": "boolean"
      +}
  2. First observedv3.0.1

TDQS

A4/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does meaningful work: it discloses that the verdict feeds acceptance statistics and that `lesson` is surfaced to the executor on its next tasks in the same project, which is a non-obvious downstream side effect. It also imposes a gating rule on accepted=True plus the constraints_verified flag. It does not address reversibility, whether feedback can be revised or overwritten, or permission requirements.

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?

The purpose is front-loaded and every sentence carries information, with no filler. The final sentence stacks four conditions plus a parenthetical into a single dense clause, which is slightly hard to parse, but nothing is redundant.

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?

An output schema exists, so return values need not be described; the remaining burden is behavioral and parameter meaning, which the description mostly covers for a 4-parameter mutation-like tool with no annotations. The gaps are whether a verdict can be revised after submission and what a rejection triggers beyond statistics.

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 description coverage is 0%, so the description must compensate and largely does: `lesson` is defined both in content ('one sentence on what to do differently, or what was right') and effect (fed to the executor later), `accepted` gets a conditional precondition, and `constraints_verified` gets the condition under which it should be set. Only `job_id` is left unexplained, which is a minor gap for 4 parameters at zero schema coverage.

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 opening sentence 'Your verdict on a delegated job' names the action (deliver a verdict) and the resource (a delegated job), which is specific enough to separate it from siblings like job_status or job_diff. It stops short of an explicit distinguishing statement such as 'call this instead of job_status when the job is finished', so it is clear but not fully sibling-differentiated.

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?

The description names a concrete prerequisite and route: for non-trivial changes, weak checks, contract constraints, or jobs with no check, accepted=True requires inspecting job_diff(job_id) first. That is real when-and-with-what guidance naming an alternative. It does not say when not to call job_feedback (e.g., one verdict per job, or what to do on rejection), leaving that to inference.

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