CREW / CrewPay

Dry-run a CREW launch (no chain tx)

crew_launch_dry_run

Read-only

Dry-run a launch (default) or wire-fees (intent=wire-fees). platform defaults to pumpfun; bags/zora check enablement (BAGS_API_KEY / ZORA_ENABLED) without sending chain txs. Prefer explicit crew[] from crew_list_kols; Autohire is a fallback. Returns dryRunId + approvalUrl. Requires CREW_AGENT_API_KEY.

Input Schema

TableJSON Schema

Name	Required	Description
`crew`	No
`mint`	No	Required when intent=wire-fees
`mode`	No
`name`	No
`seats`	No
`intent`	No	launch (default) or wire-fees
`ticker`	No
`twitter`	No
`website`	No
`imageUrl`	No	Public image URL (or use imageBase64)
`platform`	No
`agentName`	No
`holderKol`	No
`secretKey`	No	FORBIDDEN — rejected if set.
`agentModel`	No
`privateKey`	No	FORBIDDEN — rejected if set.
`description`	No	≤204 chars; attribution appended to reach ≤240 final
`imageBase64`	No
`launcherKey`	No	FORBIDDEN — rejected if set. Use CREW_LAUNCHER_KEY in MCP env only.
`initialBuySol`	No
`agentObjective`	No
`launcherPubkey`	No	Optional public launcher address for balance check (never a secret)

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedOct 12, 2026
- addedInput schema / properties / crew / items / properties / evmWallet
```
Added value: +{
+  "maxLength": 42,
+  "minLength": 42,
+  "type": "string"
+}
```
- changedInput schema / properties / crew / items / properties / wallet / minLength
```
Previous value: -32New value: +20
```
- changedInput schema / properties / crew / maxItems
```
Previous value: -8New value: +100
```
- changedInput schema / properties / launcherPubkey / minLength
```
Previous value: -32New value: +20
```
- addedInput schema / properties / platform
```
Added value: +{
+  "enum": [
+    "pumpfun",
+    "bags",
+    "zora"
+  ],
+  "type": "string"
+}
```
Changed2 schema fields changedOct 11, 2026
- changedInput schema / properties / crew / maxItems
```
Previous value: -10New value: +8
```
- changedInput schema / properties / seats / maximum
```
Previous value: -10New value: +8
```

Changed3 schema fields changedOct 11, 2026

addedInput schema / properties / intent

Added value: +{
+  "description": "launch (default) or wire-fees",
+  "enum": [
+    "launch",
+    "wire-fees"
+  ],
+  "type": "string"
+}

addedInput schema / properties / mint

Added value: +{
+  "description": "Required when intent=wire-fees",
+  "maxLength": 64,
+  "minLength": 32,
+  "pattern": "^[1-9A-HJ-NP-Za-km-z]{32,64}$",
+  "type": "string"
+}

removedInput schema / required

Removed value: -[
-  "name",
-  "ticker"
-]

First observedOct 10, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Annotations already cover readOnlyHint/openWorldHint, but the description adds substantial context beyond them: it confirms no chain txs are sent, that bags/zora gate on BAGS_API_KEY/ZORA_ENABLED, that CREW_AGENT_API_KEY is required, and that it returns dryRunId + approvalUrl. This is exactly the side-effect and auth detail an agent needs and does not contradict readOnlyHint.

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?

Four tight sentences, front-loaded with the core purpose and mode split, then platform behavior, crew guidance, and return/auth facts. Each sentence carries distinct information with no filler.

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 22-param tool with no output schema, the description supplies the essential behavioral envelope: side-effect scope, auth, platform enablement, and return values. The main residual gap is the semantics of the many loosely-documented launch/content parameters, which the description does not reach.

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?

With 22 parameters at only 36% schema description coverage, the description must carry weight, and it does explain intent (launch/wire-fees), the platform default (pumpfun) and crew[] sourcing. However, the large majority of params (mode, seats, ticker, name, socials, image fields, agentModel, etc.) get no semantic explanation in either place, so it only partially compensates.

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+resource (dry-run a CREW launch) and immediately distinguishes its two modes (launch vs wire-fees). It also differentiates from siblings by naming crew_list_kols as the preferred crew source and Autohire as a fallback, so an agent can tell it apart from crew_launch and crew_autohire without opening a schema.

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

Usage Guidelines4/5

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

Gives explicit routing guidance: 'Prefer explicit crew[] from crew_list_kols; Autohire is a fallback,' which names the alternative and the condition that selects it. It also flags the auth prerequisite (CREW_AGENT_API_KEY). It stops short of stating when to prefer this dry-run over the real crew_launch, so it is strong but not exhaustive.

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

All CREW / CrewPay 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.

Dry-run a CREW launch (no chain tx)

Input Schema

Schema Changelog

TDQS

Glama MCP Gateway

Resources