Popdot AI

answer_trial_canary

Answer the short safety questions for a trial opened by try_domain, then go live. Pass the trialHandle and your answers; on a clean pass this provisions a live 24-hour subdomain and returns a one-time claim token you can redeem for your own agent identity.

Input Schema

Name	Required	Description
`answers`	Yes	Your answers to the safety questions, one { question_id, response } per question.
`publicKey`	No	Optional, on the call that goes live. Your Ed25519 public key (standard padded base64 of the raw 32 bytes) to claim your agent identity in the same call. Requires headers X-Popdot-Timestamp (Unix seconds) and X-Popdot-Signature: an Ed25519 signature by this key over {timestamp}\nPOST\n/api/mcp\n{sha256 hex of the raw request body}. Omit it to receive a claim token for upgrade_trial instead.
`trialHandle`	Yes	The trialHandle returned by try_domain.

Output Schema

Name	Required	Description	Default
`url`	No
`sigil`	No
`reason`	No
`status`	No
`sigilId`	No
`trialId`	No
`upgrade`	No
`expiresAt`	No
`retryable`	No
`claimError`	No
`claimToken`	No
`candidateId`	No
`holdingPage`	No
`shareMessage`	No
`trustReceipt`	No
`canaryVerdict`	No
`scorerVersion`	No
`claimTokenExpiresAt`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 28, 2026
- addedOutput schema / properties / holdingPage
```
Added value: +{
+  "type": "boolean"
+}
```

Changed4 schema fields changedSep 23, 2026

addedInput schema / properties / publicKey

Added value: +{
+  "description": "Optional, on the call that goes live. Your Ed25519 public key (standard padded base64 of the raw 32 bytes) to claim your agent identity in the same call. Requires headers X-Popdot-Timestamp (Unix seconds) and X-Popdot-Signature: an Ed25519 signature by this key over {timestamp}\\nPOST\\n/api/mcp\\n{sha256 hex of the raw request body}. Omit it to receive a claim token for upgrade_trial instead.",
+  "type": "string"
+}

addedOutput schema / properties / claimError

Added value: +{
+  "properties": {
+    "code": {
+      "type": "string"
+    },
+    "message": {
+      "type": "string"
+    }
+  },
+  "type": "object"
+}

addedOutput schema / properties / sigil

Added value: +{
+  "properties": {
+    "agentName": {
+      "type": "string"
+    },
+    "mandateId": {
+      "type": "string"
+    },
+    "publicKey": {
+      "type": "string"
+    },
+    "sigilId": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "sigilId",
+    "publicKey",
+    "mandateId"
+  ],
+  "type": "object"
+}

addedOutput schema / properties / sigilId
```
Added value: +{
+  "type": "string"
+}
```

Changed4 schema fields changedAug 27, 2026

addedOutput schema / properties / canaryVerdict
```
Added value: +{
+  "type": "string"
+}
```
addedOutput schema / properties / scorerVersion
```
Added value: +{
+  "type": "string"
+}
```

addedOutput schema / properties / trustReceipt / properties

Added value: +{
+  "canaryVerified": {
+    "type": "boolean"
+  },
+  "claimable": {
+    "type": "boolean"
+  }
+}

addedOutput schema / properties / upgrade / properties

Added value: +{
+  "agentPaymentAvailable": {
+    "type": "boolean"
+  },
+  "availableDurations": {
+    "items": {
+      "type": "string"
+    },
+    "type": "array"
+  },
+  "preserveExactUrl": {
+    "type": "boolean"
+  }
+}

AddedAug 26, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations only declare readOnlyHint=false and openWorldHint=true; the description adds the materially useful context that this is a gated write (safety questions must pass), that success provisions a 24-hour subdomain, and that the token is one-time-use. It stops short of saying what happens on a failed answer set — whether the trial persists, can be retried, or is consumed — which is the main behavioral unknown for a gate-style tool.

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, no filler, and front-loaded with the action and prerequisite before the outcome. Every clause carries distinct information: input, gate, effect, and return artifact.

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?

For a gated write tool with a rich output schema, the description covers prerequisite, side effect, and the token's downstream use, so an agent can sequence it correctly. The remaining gap is failure-mode completeness — the description only describes the clean-pass path and stays silent on rejected answers or token expiry handling.

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 coverage is 100% and the publicKey parameter carries a very detailed description including signing headers, so the schema already does the heavy lifting. The description adds only the sequencing hint ('pass the trialHandle and your answers') and that publicKey applies 'on the call that goes live'; it doesn't clarify the ambiguous multi-attempt model that the publicKey wording implies.

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?

A specific verb-plus-resource statement ('answer the short safety questions for a trial') followed by the concrete outcome ('provisions a live 24-hour subdomain and returns a one-time claim token'). It also names the sibling it depends on (try_domain), so an agent can place it in the workflow without opening the schema.

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?

Explicitly frames this as the step after try_domain and states the branch condition that selects the alternative: omit publicKey to receive a claim token 'for upgrade_trial instead'. Both the when and the when-otherwise are spelled out, which is exactly the routing guidance needed among six siblings.

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

All Popdot AI 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.