iwant.fyi - find the exact car for your user

Ask iwant.fyi to find something (conversational)

demand.ask

Read-only

Talk to iwant.fyi in plain language to find something to buy. Call this when the user's request is conversational or incomplete -- e.g. 'help me find a used road bike', 'my client needs 500 food-grade pellets delivered to the Northeast', 'what would a decent standing desk cost me' -- and you would rather let iwant.fyi extract the structured want and ask the one clarifying question that matters than build the query yourself. Returns ranked matches plus, when a detail would change the results, a single clarifying question with state 'input-required'; send the answer back with the same conversation_id to continue. Prefer demand.search when you already have a clean title and constraints. Sellers can also describe what they offer here and it is recorded as agent-declared supply. Nothing is saved as a Want; use demand.create_want to commit.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`message`	Yes	What the user wants, in plain language. Include budget, condition, and location when known.
`conversation_id`	No	Returned by a prior demand.ask call. Pass it back to continue the same conversation (for example to answer a clarifying question).

Output Schema

TableJSON Schema

Name	Required	Description
`reply`	Yes	What to tell the user
`state`	Yes	completed or input-required
`intent`	No
`matches`	No
`match_count`	No
`conversation_id`	Yes
`clarifying_question`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 10, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "properties": {
+    "clarifying_question": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "conversation_id": {
+      "type": "string"
+    },
+    "intent": {
+      "type": "string"
+    },
+    "match_count": {
+      "type": "integer"
+    },
+    "matches": {
+      "items": {
+        "additionalProperties": true,
+        "description": "One purchasable match",
+        "properties": {
+          "condition": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "go_url": {
+            "description": "Tracked link to the product page; prefer this when showing a link",
+            "type": "string"
+          },
+          "id": {
+            "type": "string"
+          },
+          "normalized_specs": {
+            "additionalProperties": true,
+            "type": "object"
+          },
+          "price_cents": {
+            "type": "integer"
+          },
+          "price_currency": {
+            "type": "string"
+          },
+          "score": {
+            "type": "number"
+          },
+          "source": {
+            "type": "string"
+          },
+          "title": {
+            "type": "string"
+          },
+          "url": {
+            "description": "Product page",
+            "type": [
+              "string",
+              "null"
+            ]
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "reply": {
+      "description": "What to tell the user",
+      "type": "string"
+    },
+    "state": {
+      "description": "completed or input-required",
+      "type": "string"
+    }
+  },
+  "required": [
+    "reply",
+    "state",
+    "conversation_id"
+  ],
+  "type": "object"
+}

AddedSep 9, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Even though readOnlyHint=true already indicates no mutation, the description adds important behavioral context: it returns ranked matches, may return a single clarifying question with state 'input-required', requires passing conversation_id back to continue, and records seller offers as agent-declared supply. It explicitly states nothing is saved as a Want, reinforcing the read-only annotation without contradicting it.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense but every sentence earns its place: it states the core behavior, provides usage triggers, gives examples, covers continuation, distinguishes the sibling, and clarifies the no-write behavior. It is front-loaded with the main purpose and uses the remaining space for high-value routing and lifecycle details.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's conversational statefulness, the description covers what it returns, when a clarifying question appears, how to continue the conversation, and when to use alternatives. The output schema handles return-value structure, and the annotations cover safety, so nothing essential is missing for an agent to select and call this correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds value beyond the schema by telling callers to include budget, condition, and location in the message, and by explaining that conversation_id is the value returned from a prior demand.ask call used to continue with a clarifying answer. This is meaningful guidance that helps an agent invoke the tool correctly.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific action and resource: talk to iwant.fyi in plain language to find something to buy. It clearly distinguishes itself from demand.search by framing ask as the right choice for conversational or incomplete requests, so an agent can tell the two apart without inspecting the schemas.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly says to call this when the request is conversational or incomplete, gives concrete examples, and directs the agent to prefer demand.search when a clean title and constraints already exist. It also explains the seller use case and instructs using demand.create_want when a Want needs to be committed.

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

All iwant.fyi - find the exact car for your user 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.