Skip to main content
Glama

Compare models

compare_models
Read-only

Compare 2-5 models on price and (optionally) on the monthly cost of one workload.

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": {
      "models": "<models>"
    },
    "name": "compare_models"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelsYes
presetNoOptional workload preset that fills in token defaults: chatbot, rag, coding_agent, research_agent. Explicit numbers override it.
input_tokensNoInput tokens per call/step
calls_per_dayNoCalls (or agent tasks) per day
output_tokensNoOutput tokens per call/step
cached_percentNoShare of input billed at the cached price, 0-100 (default 50 if steps_per_task>1, else 0)
steps_per_taskNoModel calls per task for multi-step agents (default 1)
reasoning_ratioNoHidden reasoning tokens per output token, billed at the output price, on reasoning-capable models only (default: the preset's value, 0.9 for agent presets and custom workloads, 0 for chatbot; 0 excludes reasoning)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / reasoning_ratio
      Added value: +{
      +  "description": "Hidden reasoning tokens per output token, billed at the output price, on reasoning-capable models only (default: the preset's value, 0.9 for agent presets and custom workloads, 0 for chatbot; 0 excludes reasoning)",
      +  "type": "number"
      +}
  2. First observed

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds that comparison can be pure price or workload-driven monthly cost, but says nothing about how the workload numbers are interpreted, what assumptions apply, or what the comparison returns beyond a cost figure.

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 no filler; the price-first framing is placed before the optional workload clause. Slightly terse given the tool's complexity, but every word 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 an 8-parameter cost model with no output schema, the description never indicates what a result looks like (per-model monthly cost? side-by-side?) or that a preset expands into defaults. The schema covers most parameters, but the overall behavior is only minimally framed.

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 coverage is 88%, so parameter meaning is largely carried by the schema itself (preset enumeration, cached_percent defaults, reasoning_ratio behavior). The description only restates the model count and the optional workload, adding little beyond the structured fields; 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 ("Compare 2-5 models on price") plus a scope constraint (2-5 models) and the optional workload dimension. It does not explicitly distinguish itself from siblings like estimate_cost or cheapest_models_for, so an agent must infer that this is the multi-model comparison path rather than a single-model cost call.

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?

"Compare 2-5 models" and "optionally ... one workload" imply the use case (multi-model, price-focused, optionally workload-based), but no alternative tool is named and there is no when-not guidance (e.g., use estimate_cost for a single model). Usage is inferable rather than stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.