Skip to main content
Glama
Sign In
AIWorkhub

AIWorkhub

by shrec
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

aiworkhub_manager_workforce_upsert

Idempotent

Create or update one repository worker model with audited, bounded validation to keep workforce definitions accurate and policy-compliant.

Instructions

MANAGER WRITE: audited bounded upsert of one repository worker model.

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": {
      "worker_id": "<worker_id>",
      "adapter_id": "<adapter_id>",
      "model": "<model>",
      "provider": "<provider>",
      "supports": "<supports>"
    },
    "name": "aiworkhub_manager_workforce_upsert"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelYesModel name, ^[A-Za-z0-9][A-Za-z0-9_.:/+-]{0,127}$.
toolsNoTool names the worker has, matched against a task's tool needs; default none.
enabledNoFalse keeps the worker in the catalog but disabled; default true.
max_riskNoHighest task risk tier the worker may take: low, medium, high or critical; default medium.medium
providerYesProvider name in the same format as worker_id; stored lowercased.
supportsYesNon-empty list of task kinds the worker can take: mechanical, code, research, linguistic, review.
worker_idYesId of the worker to create or update, ^[A-Za-z0-9][A-Za-z0-9_.:-]{0,127}$; an existing id is updated in place, at most 64 workers exist.
adapter_idYesAdapter that runs the worker; it must be one that repository policy allows.
quality_ceilingNoHighest quality floor the worker can meet, a float in [0, 1]; tasks demanding more exclude it; default 1.0.
max_context_tokensNoLargest context in tokens the worker can take, 0-10,000,000; tasks needing more exclude it; default 0.
manager_score_adjustmentNoManager adjustment added to the worker's routing success score, in percentage points from -20 to 20; default 0.0.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed11 schema fields changedv0.12.67
    • addedInput schema / properties / adapter_id / description
      Added value: +"Adapter that runs the worker; it must be one that repository policy allows."
    • addedInput schema / properties / enabled / description
      Added value: +"False keeps the worker in the catalog but disabled; default true."
    • addedInput schema / properties / manager_score_adjustment / description
      Added value: +"Manager adjustment added to the worker's routing success score, in percentage points from -20 to 20; default 0.0."
    • addedInput schema / properties / max_context_tokens / description
      Added value: +"Largest context in tokens the worker can take, 0-10,000,000; tasks needing more exclude it; default 0."
    • addedInput schema / properties / max_risk / description
      Added value: +"Highest task risk tier the worker may take: low, medium, high or critical; default medium."
    • addedInput schema / properties / model / description
      Added value: +"Model name, ^[A-Za-z0-9][A-Za-z0-9_.:/+-]{0,127}$."
    • addedInput schema / properties / provider / description
      Added value: +"Provider name in the same format as worker_id; stored lowercased."
    • addedInput schema / properties / quality_ceiling / description
      Added value: +"Highest quality floor the worker can meet, a float in [0, 1]; tasks demanding more exclude it; default 1.0."
    • addedInput schema / properties / supports / description
      Added value: +"Non-empty list of task kinds the worker can take: mechanical, code, research, linguistic, review."
    • addedInput schema / properties / tools / description
      Added value: +"Tool names the worker has, matched against a task's tool needs; default none."
    • addedInput schema / properties / worker_id / description
      Added value: +"Id of the worker to create or update, ^[A-Za-z0-9][A-Za-z0-9_.:-]{0,127}$; an existing id is updated in place, at most 64 workers exist."
  2. First observedv0.1.0

TDQS

B3.1/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the mutation and idempotency profile is covered. The description adds 'audited' and 'bounded', hinting at audit logging and limits, but never says what is audited or what the bounds are (the 64-worker cap appears only in the worker_id schema description).

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?

A single dense sentence with zero filler and the operation class front-loaded. For an 11-parameter mutation tool it is arguably too short, but no sentence is wasted.

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

Completeness2/5

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

Given a manager-level mutation with 11 parameters and policy constraints ('adapter must be one repository policy allows', 64-worker cap), the description is too thin. The output schema and rich param docs relieve some burden, but 'audited bounded' is never unpacked, leaving real behavioral context undisclosed.

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 all 11 parameters are already documented richly (formats, defaults, ranges). The description contributes nothing about parameters, so the baseline 3 for full-coverage schemas 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?

States a specific verb (upsert) and resource (one repository worker model) with the 'MANAGER WRITE' prefix adding the operation class. It is distinguishable from the read-only siblings workforce_catalog and workforce_rank, though the description never names them explicitly to route the agent.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use or when-not-to-use guidance and no named alternative. The only hint is the word 'upsert', which implies create-or-update, leaving the agent to infer that workforce_catalog is for reading the same entities.

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