Skip to main content
Glama
Sign In
subtask

subtask

by tedin7
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

review

Prepares or submits an advisory assessment of a terminal delivery against parent criteria, building local evidence packets by default and sending one request only with submit.

Instructions

Advisory Jev review of a terminal delivery against the parent's criteria (1-12). Read the automatic outcome in wait()/result first; do not resubmit the same delivery. Default prepares a local evidence packet without network; packets=True prepares separate claim packets and manifests offline (never submits). submit=True sends one request (unknown sends are never retried). Supply original_request from the coordinator to judge full scope; without it scope_assessment is unproven, which is neither a pass nor a contradiction. supported is advice, not acceptance. provider_choice is the raw answer; assessment includes local vetoes (missing, failed or mismatched evidence), which are not findings by the model. Jev never accepts, merges, deploys or retries the worker; local checks remain necessary. Key/budget errors are final for the call: keys only from subtask jev setup, never a tool argument.

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": {
      "id": "<id>",
      "criteria": "<criteria>"
    },
    "name": "review"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYes
submitNo
packetsNo
criteriaYes
original_requestNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
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 so well: default runs offline, packets=True never submits, submit=True sends exactly one request with unknown sends never retried, key/budget errors are terminal for the call, and keys must come from `subtask jev setup`, never a tool argument. It also warns that the tool never accepts, merges, deploys or retries the worker and that local vetoes are not model findings. Remaining gaps are the cost/latency profile of submit=True and what a failed request returns.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

There is no filler and the purpose is front-loaded, but the text is a semicolon-chained block where mode selection, output semantics, and credential rules are interleaved with parenthetical asides. Splitting the offline/packets/submit modes into a short enumerated structure would make the same content markedly easier to scan.

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?

For a five-parameter, no-annotation tool with no output schema, it covers side effects, network behavior, credential sourcing and even names key return fields (scope_assessment, supported, provider_choice, assessment). The shortfall is that `id` and `criteria` semantics are left implicit, so an agent could invoke it correctly but not confidently build arguments.

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 0%, so the description must compensate and it only partly does: submit, packets and original_request are each given clear semantics and consequences, including the unproven-scope fallback. The two required parameters are much weaker — `id` is never explained (presumably a delivery identifier) and `criteria` is only hinted at via 'the parent's criteria (1-12)', with no note on format or whether all twelve are needed.

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 object: an advisory review of a terminal delivery judged against the parent's 1-12 criteria. It also distinguishes itself from the automatic path by pointing at wait()/result. It falls short of 5 because 'Jev review' and 'terminal delivery' are unexplained domain jargon, so an agent without context cannot fully picture what the review produces.

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?

Gives concrete routing advice: read the automatic outcome in wait()/result first and do not resubmit the same delivery, then enumerates the three operating modes (default/packets/submit) with the condition for each. It also says when the result is trustworthy (supply original_request or scope_assessment is unproven). It stops short of naming non-review alternatives such as consensus or an explicit 'do not use when' case.

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