get_modelsGet all vehicle models for a make and year. Returns model names and IDs. E.g., make 'Toyota', year '2023'.
| Name | Required | Description | Default |
|---|---|---|---|
| make | Yes | Vehicle make name (e.g., "Toyota", "Ford", "BMW") | |
| year | Yes | Model year (e.g., 2022) |
| Name | Required | Description | Default |
|---|---|---|---|
| make | Yes | Vehicle make name | |
| year | Yes | Model year | |
| count | Yes | Total count of models | |
| models | Yes | List of vehicle models |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Output schema / (root)Previous value: -nullNew value: +{
+ "properties": {
+ "count": {
+ "description": "Total count of models",
+ "type": "number"
+ },
+ "make": {
+ "description": "Vehicle make name",
+ "type": "string"
+ },
+ "models": {
+ "description": "List of vehicle models",
+ "items": {
+ "properties": {
+ "make_id": {
+ "description": "Make ID",
+ "type": [
+ "number",
+ "null"
+ ]
+ },
+ "make_name": {
+ "description": "Make name",
+ "type": [
+ "string",
+ "null"
+ ]
+ },
+ "model_id": {
+ "description": "Model ID",
+ "type": [
+ "number",
+ "null"
+ ]
+ },
+ "model_name": {
+ "description": "Model name",
+ "type": [
+ "string",
+ "null"
+ ]
+ }
+ },
+ "required": [
+ "make_id",
+ "make_name",
+ "model_id",
+ "model_name"
+ ],
+ "type": "object"
+ },
+ "type": "array"
+ },
+ "year": {
+ "description": "Model year",
+ "type": "number"
+ }
+ },
+ "required": [
+ "make",
+ "year",
+ "count",
+ "models"
+ ],
+ "type": "object"
+}Input schema / examplesAdded value: +[
+ {
+ "make": "Toyota",
+ "year": 2023
+ },
+ {
+ "make": "Ford",
+ "year": 2022
+ }
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, covering the safety profile. The description adds the useful detail that the response contains model names and IDs, but it does not disclose any additional behavioral traits beyond what annotations or schema imply. No contradiction exists.
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?
The description is concise (two short sentences plus an example), front-loads the core action, and avoids redundant filler. Every sentence contributes to understanding the tool's purpose and usage.
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?
Given the small parameter count, rich annotations, and existence of an output schema, the description is adequately complete. It conveys the essential inputs, expected output type, and a usage example. It doesn't need to detail return values since the output schema covers that.
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%, so the schema already describes both 'make' and 'year' with examples. The description's example (Toyota, 2023) adds minimal extra meaning beyond the schema, which is sufficient for a baseline score.
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?
The description states exactly what the tool does: 'Get all vehicle models for a make and year' and specifies the output ('model names and IDs'). This distinguishes it from sibling tools like get_makes by focusing on models rather than makes, and the verb+resource structure is specific and clear.
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?
The description clearly implies the usage context: this tool is for retrieving models when the user supplies a make and year. It provides a concrete example (Toyota, 2023) that reinforces the expected inputs. However, it does not explicitly mention alternatives or when not to use it, so it falls short of a 5.
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.
The descriptions are extraordinarily detailed and do a lot of work to differentiate tools, but there is real functional overlap: three ask_pipeworx variants, six Polymarket/bet tools (bet_research, polymarket_edges, polymarket_edge_tracker, polymarket_arbitrage, polymarket_fill_risk, polymarket_kalshi_spread) that all target identifying betting/value opportunities, and overlapping ai_visibility_check vs scan_competitor_ai_presence. A capable agent could navigate it, but misselection risk is high.
Mostly snake_case and readable, but the verb/noun placement is inconsistent: verb-first (get_makes, list_subscriptions, resolve_entity, decode_vin) mixes with noun-first (entity_profile, bet_research, pipeworx_trending) and branded prefixes (ask_pipeworx, pipeworx_feedback, polymarket_*). No chaotic camelCase mixing, but no single predictable pattern either.
37 tools is well beyond the heavy threshold, and the server named 'Nhtsa' carries only ~6 vehicle-specific tools while the rest is a general-purpose research platform spanning prediction markets, memory, npm packages, AI-marketing audits, and subscriptions. The scope is overloaded and the name badly misrepresents the content, making the surface feel sprawling rather than focused.
For the NHTSA vehicle domain it covers the lookup surface well (makes, models, recalls, complaints, safety ratings, VIN decode), and the broader research platform is genuinely deep with grounding, grounding-with-evidence, discovery, subscription, and memory support. Minor gaps exist (no direct vehicle-make year filtering beyond three fields, USPTO patent APIs are soft-failing), but no dead ends for core workflows.