Store API

Сравнить модели

compare_models

Ask 2 to 4 models the same question at once and get their answers side by side with token counts. Every model is billed separately. — Задать один вопрос нескольким моделям сразу и сравнить ответы.

Input Schema

TableJSON Schema

Name	Required	Description
`models`	Yes	2 to 4 model slugs from list_models, e.g. openai/gpt-6-sol and anthropic/claude-sonnet-5
`prompt`	Yes	Question or task, the same for every model
`system`	No	System instruction, optional
`max_tokens`	No	Answer length limit for each model, 600 by default

Output Schema

TableJSON Schema

Name	Required	Description	Default
`answers`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 24, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "answers": {
+      "items": {
+        "properties": {
+          "answer": {
+            "type": "string"
+          },
+          "error": {
+            "type": "string"
+          },
+          "input_tokens": {
+            "type": "number"
+          },
+          "model": {
+            "type": "string"
+          },
+          "output_tokens": {
+            "type": "number"
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    }
+  },
+  "type": "object"
+}

AddedSep 24, 2026

TDQS

B3.4/5.0

Behavior3/5

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

Annotations indicate this is not read-only (mutation possible) and not idempotent. The description discloses that billing occurs for each model, which is useful for cost awareness. It does not mention any side effects beyond costs, but it also doesn't state that it sends prompts to external APIs, which could be inferred. The billing disclosure adds value beyond the annotations.

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 description is two sentences long, front-loaded with the core functionality and key constraint (2-4 models). The bilingual addition is redundant and could be considered waste, but the core is concise. It earns a 4 for being mostly efficient.

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 tool with an output schema and full schema coverage, the description is adequate but not complete. It lacks guidance on expected output structure (though output schema exists), error scenarios, or cost implications beyond billing. Given the complexity of multi-model queries, it could benefit from more context, but the essentials are present.

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 fully documents parameters. The description adds minimal extra semantics beyond the schema, excepting the billing note. It does not elaborate on the behavior of max_tokens or system, but the schema covers this, so a baseline of 3 is appropriate.

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 clearly states the action (ask a question to 2-4 models at once) and the outcome (get answers side by side with token counts), effectively distinguishing it from the sibling tool ask_model which handles single-model queries. However, it doesn't explicitly mention the comparison aspect as a differentiator, though the side-by-side display is implied.

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 implies usage for comparing multiple models, but does not explicitly state when to use this tool instead of ask_model (single model) or provide exclusion criteria. The mention of 'every model is billed separately' gives a cost consideration, but there's no clear routing guidance.

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

All Store API tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.