Skip to main content
Glama
Sign In
Precedent

Precedent

by prabhaingit
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Local

predict

Forecast an order's target value from an existing order_id or new field values, returning the result, confidence, and runner-up options.

Instructions

Predict the target value for one order with the full model (all past orders in context).

Give either order_id (a held-out order, see list_orders) or fields (a dict of field values for a new order). Returns the predicted value, the model's confidence and the runners-up.

Args: order_id: index of a held-out order. fields: field values for a new order, as an alternative to order_id. model: "fast" (TabPFN-3.5-Fast) or "base" (TabPFN-3.5). Both run locally.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "predict"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelNofast
fieldsNo
order_idNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.6/5.0
Behavior3/5

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

No annotations are provided, so the description carries the full behavioral burden. It usefully discloses that the model runs locally, includes all past orders in context, and returns the predicted value, confidence, and runners-up. It omits permissions, side effects, error behavior, and whether the operation is read-only.

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 core purpose, inputs, and return values are front-loaded and easy to scan. There is some redundancy because order_id and fields are described both in the main paragraph and again in the Args section, but the description remains appropriately sized.

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?

With no output schema and no annotations, the description does a good job covering the main call context: input alternatives, model names, local execution, and returned prediction details. It could be more complete by stating whether exactly one of order_id or fields is required and by describing the returned format more precisely.

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 description coverage is 0%, so the description must compensate. It defines all three parameters: order_id as a held-out order index, fields as values for a new order, and model as either 'fast' (TabPFN-3.5-Fast) or 'base' (TabPFN-3.5). It does not clarify exclusivity rules or the full structure of the fields dictionary.

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 description gives a specific verb and resource: predict the target value for one order using the full model with all past orders in context. It also references list_orders for held-out orders, but it does not explicitly differentiate itself from the other siblings such as explain or verify.

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?

The description explains that the caller should provide either order_id or fields, and names the two model choices. However, it does not state when to use this tool instead of explain, verify, or list_orders beyond the note that held-out order IDs come from list_orders. Usage is implied rather than fully guided.

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