Get detailed specs for an AI model: context window, pricing per 1K tokens, knowledge cutoff, provider, multimodal support, reasoning capabilities, and feature list. Covers 30+ models from OpenAI, Anthropic, Google, DeepSeek, Meta, Mistral, Cohere, xAI.
| Name | Required | Description | Default |
|---|---|---|---|
| model | Yes | Model name (e.g. "gpt-4o", "claude-3.5-sonnet", "gemini-3.1-pro-preview") |
| Name | Required | Description | Default |
|---|---|---|---|
| model | No | ||
| pricing_per_1k | No |
Changes observed during successful MCP inspections.
Input schema / examplesAdded value: +[
+ {
+ "model": "gpt-4o"
+ }
+]Input schema / properties / model / descriptionPrevious value: -"Model name (e.g. \"gpt-4o\", \"claude-3.5-sonnet\", \"gemini-2.5-pro\")"New value: +"Model name (e.g. \"gpt-4o\", \"claude-3.5-sonnet\", \"gemini-3.1-pro-preview\")"Output schema / propertiesAdded value: +{
+ "model": {},
+ "pricing_per_1k": {
+ "type": "object"
+ }
+}Output schema / (root)Previous value: -nullNew value: +{
+ "additionalProperties": true,
+ "type": "object"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, so the safety profile is fully covered and the description's '30+ models' line usefully reinforces that this is a closed, static dataset. It does not disclose what happens on an unknown/ambiguous model name (error vs. nearest match) or whether the data can be stale, which are the remaining behavioral unknowns for a lookup tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, front-loaded with the verb and resource, then the return fields, then coverage. The provider roll-call is slightly padded but does convey breadth of catalog in few words; nothing is wasted or buried.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With an output schema present the description needn't explain return values, and it correctly spends its words on scope and catalog coverage instead. Missing only edge-case behavior for unrecognized model names, which is a minor gap for a static reference lookup.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% and the single 'model' parameter already carries examples, so the schema does the work. The description adds no syntax rules (exact-match vs. alias handling, whether provider prefix like 'openai/gpt-4o' is accepted), so it does not rise above the baseline for a fully documented parameter.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
A specific verb+resource ('Get detailed specs for an AI model') followed by an enumerated field list (context window, pricing, cutoff, provider, multimodal, reasoning, features) makes the payload unmistakable. It also scopes the catalog ('30+ models from OpenAI, Anthropic, Google...'), which implicitly separates it from a live/single-provider tool, but it never names the closest siblings (list_llm_models, compare_models, context_window_check), so differentiation is inferred rather than stated.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Usage is only implied: an agent can infer this is the lookup to call when it needs static facts about a named model. There is no when-to-use/when-not statement, no mention of list_llm_models for discovery or compare_models for side-by-side comparison, and no guidance on what to do when a model isn't in the static catalog.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.