Skip to main content
Glama

Recommend a model for delegate_task

recommend_model
Read-only

Returns ranked provider, model, and effort recommendations for a delegated child task before execution, with fallback candidates if the first cannot start or hits a usage limit.

Instructions

Call before every child task, including ones you would start with your native subagent tool. Returns 1-3 candidates, best first; pass a candidate's providerInstanceId, model and options as delegate_task.target (sameAsOrchestrator: true means your native subagent tool also works). If the first cannot start or hits a usage limit, use the next. Always pass taskType, one of:

  • review: Independent review of code, a PR, a plan or a document.

  • debug: Find and fix a bug, a failing test or a crash.

  • plan: Architecture, design docs, breaking work down.

  • research: Web or codebase research, comparisons, reading docs.

  • quick: Small mechanical edits; renames, formatting, bumps.

  • code: Implement a feature, refactor, write tests.

  • design: UI, visual and UX work.

  • writing: Prose, docs, posts, emails, copy.

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": "<task>"
    },
    "name": "recommend_model"
  }
}

Input Schema

NameRequiredDescriptionDefault
sizeNoRough size of the task. Shifts effort.
taskYesOne line describing what the child will do.
usageNoOptional usage percentages per provider instance, if you know them (e.g. from /usage-limits).
taskTypeNoTask type from the list in the description. Pass it; the keyword classifier is only a last resort.
criticalityNoHow costly a mistake is. Shifts effort.
capabilitiesNoOutput of T3 Code's orchestrator_capabilities, as returned (object, JSON string, providers array, or a list of outputs). Needed on the first call; later calls reuse the last one received.
mergeCapabilitiesNoMerge `capabilities` into the ones kept from earlier calls (use it for orchestrator_capabilities `search` output).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.5/5.0
Behavior4/5

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

Annotations only declare readOnlyHint=true and openWorldHint=false; the description adds genuinely new behavior: return cardinality and ordering, fallback chaining between candidates, the sameAsOrchestrator escape hatch, and cross-call state (capabilities reused from the last call unless mergeCapabilities is set). It does not say what happens when no candidate is returned or how failures other than usage limits surface, which keeps it short of a 5.

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 imperative call-to-action and the return/fallback contract before the long taskType list, so the critical instructions are read first. The eight-bullet enumeration is long but each entry disambiguates a real choice; there is minor repetition between 'Always pass taskType' and the schema note about the keyword classifier.

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 7-parameter, stateful recommendation tool with no output schema, the description covers invocation timing, result shape, fallback, downstream wiring, capability caching, and the taxonomy needed to fill taskType. Remaining gaps are edge behavior: empty candidate lists and how non-usage-limit failures are reported.

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 coverage is 100%, so the baseline is 3. The description earns above baseline because the taskType enumeration — eight categories with definitions — exists only in prose and the schema literally defers to it ('Task type from the list in the description'), making the description load-bearing for the tool's key parameter. size, criticality and capabilities are left to the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb+resource (recommend 1-3 model candidates) and states the exact downstream use: pass a candidate's providerInstanceId, model and options as delegate_task.target. It is plainly distinct from the siblings get_stats, log_delegation and log_outcome, and an agent can tell immediately what it gets back (ranked candidates, best first).

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

Usage Guidelines5/5

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

Explicit trigger: 'Call before every child task, including ones you would start with your native subagent tool.' Explicit fallback: 'If the first cannot start or hits a usage limit, use the next.' It also mandates taskType on every call, leaving nothing about when/how to call it to inference.

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