TaskBullet Site Guide

match_intent

Read-onlyIdempotent

Classify what a visitor or their AI wants from taskbullet.com (hire a VA, apply for a job, existing client, or Agent API) and return the next URL. Job seekers are never hire conversions.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`message`	Yes	What the visitor said or asked. Capped at 2000 characters.
`pageUrl`	No	Optional page they are on. Capped at 500 characters.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`ask`	Yes
`reply`	Yes
`audience`	Yes
`nextUrls`	Yes
`isHireConversion`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedOct 16, 2026

changedInput schema / properties / message / description

Previous value: -"What the visitor said or asked."New value: +"What the visitor said or asked. Capped at 2000 characters."

addedInput schema / properties / message / maxLength
```
Added value: +2000
```

changedInput schema / properties / pageUrl / description

Previous value: -"Optional page they are on."New value: +"Optional page they are on. Capped at 500 characters."

addedInput schema / properties / pageUrl / maxLength
```
Added value: +500
```

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": false,
+  "properties": {
+    "ask": {
+      "type": "string"
+    },
+    "audience": {
+      "enum": [
+        "hire_va",
+        "work_va",
+        "needs_intent",
+        "existing_client",
+        "ai_agent"
+      ],
+      "type": "string"
+    },
+    "isHireConversion": {
+      "type": "boolean"
+    },
+    "nextUrls": {
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "label": {
+            "type": "string"
+          },
+          "url": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "label",
+          "url"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "reply": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "audience",
+    "isHireConversion",
+    "ask",
+    "reply",
+    "nextUrls"
+  ],
+  "type": "object"
+}

First observedOct 16, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description only needs to add domain behavior. It does: the business rule that job-seeker traffic is never treated as a hire conversion, which materially affects how the classification result should be interpreted and cannot be inferred from annotations.

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?

Two sentences, zero filler. The purpose and intent categories come first, the return value second, and the exception rule last where it belongs.

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

Completeness4/5

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 need not detail the response shape, and it is complete on inputs and intent taxonomy. It stops just short of distinguishing this classifier from the similarly oriented recommend_path sibling, which is the one thing an agent might still second-guess.

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% with only two parameters (message, pageUrl) and both are documented in the schema with their caps. The description adds no format syntax, examples, or guidance on how pageUrl affects classification, so baseline 3 is appropriate.

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?

States a specific verb (classify) and resource (visitor/AI intent on taskbullet.com) and enumerates the actual intent classes it resolves: hire a VA, apply for a job, existing client, Agent API. It also names the output (the next URL), so an agent knows what comes back without opening the output schema.

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?

Usage is implied: call this to route a visitor based on a free-text message. However, it never says when to prefer it over siblings like recommend_path or understand_site, and no prerequisites or exclusions for the tool itself are given — the only routing rule ('Job seekers are never hire conversions') governs classification output, not tool selection.

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

All TaskBullet Site Guide 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.