Skip to main content
Glama
Sign In
AIWorkhub

AIWorkhub

by shrec
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

aiworkhub_manager_workforce_rank

Read-only

Ranks available workers for a task and explains why each is selected or excluded, filtering by work kind, risk, quality floor, context size and tool needs.

Instructions

MANAGER READ: explainable cheapest-capable routing from current evidence.

detail="summary" (default) keeps every top-level selection field (selected_*, economic_advisory, etc.) exact; the selected compatible candidate and the next two keep their full row, every other compatible candidate is reduced to worker_id/adapter_id/model/score; excluded candidates are reduced to a count per exclusion reason plus the first 10 as worker_id/adapter_id/model. detail="evidence" behaves like "full": both return today's payload exactly.

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": {
      "task_id": "<task_id>",
      "kinds": "<kinds>"
    },
    "name": "aiworkhub_manager_workforce_rank"
  }
}

Input Schema

NameRequiredDescriptionDefault
riskNoTask risk: low, medium (default), high or critical; workers whose max_risk is lower are excluded.medium
kindsYesWork kinds the task needs, from mechanical, code, research, linguistic and review; at least one, and a worker must support every kind listed.
detailNosummary (default) shrinks non-selected candidates to short rows; evidence and full both return the complete payload.summary
task_idYesId of the task the ranking is for; must be non-blank.
tool_needsNoTools or capabilities the task needs, default none; workers lacking one are excluded.
quality_floorNoMinimum quality from 0.0 to 1.0 (clamped), default 0.0; workers whose quality_ceiling is below it are excluded.
context_tokensNoEstimated context the task needs in tokens, default 0 for no requirement; workers with a smaller max_context_tokens are excluded.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changedv0.12.67
    • addedInput schema / properties / context_tokens / description
      Added value: +"Estimated context the task needs in tokens, default 0 for no requirement; workers with a smaller max_context_tokens are excluded."
    • addedInput schema / properties / detail / description
      Added value: +"summary (default) shrinks non-selected candidates to short rows; evidence and full both return the complete payload."
    • addedInput schema / properties / kinds / description
      Added value: +"Work kinds the task needs, from mechanical, code, research, linguistic and review; at least one, and a worker must support every kind listed."
    • addedInput schema / properties / quality_floor / description
      Added value: +"Minimum quality from 0.0 to 1.0 (clamped), default 0.0; workers whose quality_ceiling is below it are excluded."
    • addedInput schema / properties / risk / description
      Added value: +"Task risk: low, medium (default), high or critical; workers whose max_risk is lower are excluded."
    • addedInput schema / properties / task_id / description
      Added value: +"Id of the task the ranking is for; must be non-blank."
    • addedInput schema / properties / tool_needs / description
      Added value: +"Tools or capabilities the task needs, default none; workers lacking one are excluded."
  2. First observedv0.1.0

TDQS

B3.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description adds meaningful behavioral detail about how output is shaped in summary mode versus evidence/full mode. It explains which candidates retain full rows, which are reduced, and how excluded candidates are represented, which is useful context beyond 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.

Conciseness4/5

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

The purpose is front-loaded in the first sentence, followed by a focused explanation of the detail modes. The description is not bloated, though it spends most of its length on output reduction details rather than broader invocation guidance.

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?

An output schema exists and all parameters are fully described in the schema, so the description does not need to restate return values. However, for a seven-parameter ranking tool, the description omits ranking criteria beyond "cheapest-capable" and provides no usage guidance relative to sibling workforce tools, leaving a contextual gap.

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 the schema already documents all seven parameters. The description adds extra meaning for the detail parameter's output-shaping behavior, but does not compensate for or expand on risk, kinds, task_id, tool_needs, quality_floor, or context_tokens beyond what the schema provides; 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 opening sentence names a specific operation type ("MANAGER READ") and frames the tool as "explainable cheapest-capable routing from current evidence," which conveys that it ranks or routes work candidates. It is clear enough to distinguish from write-oriented siblings like workforce_upsert, though it never explicitly names workforce_catalog as the alternative.

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?

The description does not state when to use this tool versus sibling tools, nor does it provide any prerequisites or exclusion conditions. "MANAGER READ" implies a read-only management operation, but there is no explicit when/when-not guidance.

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