Skip to main content
Glama
UplinkSwitch MCP server

UplinkSwitch MCP server

Official
by uplinkswitch

compare_prices

Compare price per million tokens across models, cheapest input first, to help agents pick the least expensive model that meets the task. Requires no API key.

Instructions

Compare price per million tokens across models, cheapest input first, so an agent can pick the least expensive model that does the job. Needs no API key.

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": "compare_prices"
  }
}

Input Schema

NameRequiredDescriptionDefault
tagNoOnly models carrying this tag, such as uncensored or reasoning
typeNoWhich kind of model to comparechat
limitNoHow many rows to return

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

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 full behavioral burden; it does disclose two useful traits: the sort order (cheapest input first) and that no API key is required, which removes an auth prerequisite. It never states that this is a read-only lookup, nor does it say where prices come from, how fresh they are, or what a row contains, leaving meaningful behavioral gaps for an unannotated tool.

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 front-loaded sentence with the core action first, followed by ordering and intent, and no filler. It is efficient, though the trailing 'Needs no API key' could arguably be tightened, and nothing is wasted.

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 simple three-parameter, zero-required read tool this covers purpose, ordering, and auth, which is close to sufficient. With no output schema, the description should say something about what each row contains (model, provider, input/output price) or whether data is a static snapshot, and it does not.

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 tag, type with its enum and default, and limit with its range and default. The description adds no parameter-level meaning such as what tag values exist or whether limit applies before or after filtering, so the baseline 3 applies.

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: comparing price per million tokens across models, with the ordering (cheapest input first) and the goal (pick the least expensive model) made explicit. It does not name or contrast itself with the siblings (model, chat, list_models), so an agent must infer that this is the cost-comparison entry point rather than a general model listing.

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 clause 'so an agent can pick the least expensive model that does the job' implies the usage context of cost-based model selection, which is helpful. There are no explicit exclusions or pointers to alternatives (e.g., use list_models to browse capabilities rather than price), so usage is suggested rather than prescribed.

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