Skip to main content
Glama

Recommend a Claude model

recommend_model

Recommends which Claude model fits a task at the start of work, helping users get good results without wasting usage.

Instructions

Call at the START of a new task. Returns which Claude model (Haiku, Sonnet, Opus, Fable) fits the task best, so the user gets good results without wasting usage. Show the returned one_liner to the user.

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
taskYesWhat the user wants to do, in their words
high_stakesNoTrue if a mistake would be costly
chat_messagesNoMessages so far in this chat
current_modelNoModel in use now, e.g. 'Opus 5.5'

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.0

TDQS

B3.4/5.0
Behavior3/5

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

With no annotations, the description must carry the behavioral burden; it implies a non-mutating recommendation call and usefully tells the agent to surface the 'one_liner' field to the user, which is behavior an agent would not otherwise know. It does not state whether the call changes any state, nor does it describe the rest of the return payload beyond one field.

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?

Three short sentences with the timing instruction front-loaded and zero filler. The final sentence about the one_liner is a distinct actionable instruction and earns its place.

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?

For a four-parameter, no-output-schema tool, the description covers the call trigger and one named return field but leaves the rest of the return shape and the effect of current_model/high_stakes on the answer unstated. Adequate to invoke, not fully complete.

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% and every parameter carries its own explanation, so the schema does the parameter work. The description adds no meaning about 'task' phrasing, 'high_stakes', or how 'current_model' influences the recommendation, which is the baseline-3 outcome.

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 resource ('returns which Claude model ... fits the task best') and names the candidate models, so the agent knows exactly what comes back. It does not explicitly distinguish itself from siblings like review_model_choice or list_models, though 'at the START of a new task' implies a pre-work recommendation role.

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

Usage Guidelines3/5

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

Gives clear timing guidance ('Call at the START of a new task'), which is real usage context. It offers no exclusions and never names the alternative tools for reviewing an existing choice or listing models, so routing between siblings is left 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