Slid Phi Labs

spl_agentic_plan

Read-onlyIdempotent

Plan one Agent Commerce Network (ACN) run without executing it: validate the run shape across Rider, Warrant, Tollkeeper, Quikgater, PCC, AWLpay, PSI, and Conductor, plus any optional stage whose spec field is present. Pure and read-only — no disk, no network, nothing is charged or started. Returns the planned stages, quote, and settlement preview. Use to dry-run a run before spl_agentic_run; use spl_agentic_context to shrink the context a run will carry.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "spl_agentic_plan"
  }
}

Input Schema

Name	Required	Description
`ops`	No	Ops-feed input for the run.
`sku`	No	SKU to buy or price; string id or object.
`url`	No	Target URL for the run.
`cuni`	No	CuNi program or exactness input for the run.
`demo`	No	True to plan or run a demo with no payment and no Rider token.
`host`	No	Target hostname for the run.
`rail`	No	Payment rail: stripe for humans, x402 for agents.
`swap`	No	Swap details for a cross-chain step (from/to chain, token, amount).
`tool`	No	Tool call spec for the run.
`agent`	No	Agent spec for the run; string id or object.
`audit`	No	Audit or audit-export input; string id or object.
`bytes`	No	Input byte count the run will process; used for the quote.
`rider`	No	Agent-Rider JWT identifying the acting agent. Required for live runs unless demo is true.
`action`	No	Run action or stage name, e.g. plan, compress, or a stage key. Determines which stages the plan includes.
`payout`	No	Payout details for the run.
`solana`	No	Solana transaction input for the run.
`dispute`	No	Dispute details for the run.
`mcpTool`	No	MCP tool call spec for the run.
`message`	No	Message payload for an agent-messaging stage.
`sandbox`	No	Sandbox spec for an isolated step.
`asyncRun`	No	Async run spec for the run.
`crossing`	No	Crossing or bridge identifier when the run moves between systems.
`depotStore`	No	Depot store input for the run.
`membership`	No	Membership input for the run.
`reputation`	No	Reputation input for the run; string id or object.
`chamberSeal`	No	Chamber seal input for the run.
`tokenBudget`	No	Token budget for the run; string id or object.
`depotBilling`	No	Depot billing input for the run.
`depotReceipt`	No	Depot receipt input for the run.
`privateBench`	No	Private benchmark input for the run.
`conductorTask`	No	Conductor task spec; string id or object.
`riderPaidCall`	No	Paid Rider call input for the run.
`standingRider`	No	Standing Rider credential for the run; string id or object.
`conductorReview`	No	Conductor review input for the run.
`warrantTemplate`	No	Warrant template to apply to the run; string id or object.

Schema Changelog

Changes observed during successful MCP inspections.

Changed35 schema fields changedNov 7, 2026

addedInput schema / properties / action / description

Added value: +"Run action or stage name, e.g. plan, compress, or a stage key. Determines which stages the plan includes."

addedInput schema / properties / agent / description

Added value: +"Agent spec for the run; string id or object."

addedInput schema / properties / asyncRun / description
```
Added value: +"Async run spec for the run."
```

addedInput schema / properties / audit / description

Added value: +"Audit or audit-export input; string id or object."

addedInput schema / properties / bytes / description

Added value: +"Input byte count the run will process; used for the quote."

addedInput schema / properties / chamberSeal / description
```
Added value: +"Chamber seal input for the run."
```
addedInput schema / properties / conductorReview / description
```
Added value: +"Conductor review input for the run."
```

addedInput schema / properties / conductorTask / description

Added value: +"Conductor task spec; string id or object."

addedInput schema / properties / crossing / description

Added value: +"Crossing or bridge identifier when the run moves between systems."

addedInput schema / properties / cuni / description

Added value: +"CuNi program or exactness input for the run."

addedInput schema / properties / demo / description

Added value: +"True to plan or run a demo with no payment and no Rider token."

addedInput schema / properties / depotBilling / description
```
Added value: +"Depot billing input for the run."
```
addedInput schema / properties / depotReceipt / description
```
Added value: +"Depot receipt input for the run."
```
addedInput schema / properties / depotStore / description
```
Added value: +"Depot store input for the run."
```
addedInput schema / properties / dispute / description
```
Added value: +"Dispute details for the run."
```
addedInput schema / properties / host / description
```
Added value: +"Target hostname for the run."
```
addedInput schema / properties / mcpTool / description
```
Added value: +"MCP tool call spec for the run."
```
addedInput schema / properties / membership / description
```
Added value: +"Membership input for the run."
```

addedInput schema / properties / message / description

Added value: +"Message payload for an agent-messaging stage."

addedInput schema / properties / ops / description
```
Added value: +"Ops-feed input for the run."
```
addedInput schema / properties / payout / description
```
Added value: +"Payout details for the run."
```
addedInput schema / properties / privateBench / description
```
Added value: +"Private benchmark input for the run."
```

addedInput schema / properties / rail / description

Added value: +"Payment rail: stripe for humans, x402 for agents."

addedInput schema / properties / reputation / description

Added value: +"Reputation input for the run; string id or object."

addedInput schema / properties / rider / description

Added value: +"Agent-Rider JWT identifying the acting agent. Required for live runs unless demo is true."

addedInput schema / properties / riderPaidCall / description
```
Added value: +"Paid Rider call input for the run."
```
addedInput schema / properties / sandbox / description
```
Added value: +"Sandbox spec for an isolated step."
```

addedInput schema / properties / sku / description

Added value: +"SKU to buy or price; string id or object."

addedInput schema / properties / solana / description

Added value: +"Solana transaction input for the run."

addedInput schema / properties / standingRider / description

Added value: +"Standing Rider credential for the run; string id or object."

addedInput schema / properties / swap / description

Added value: +"Swap details for a cross-chain step (from/to chain, token, amount)."

addedInput schema / properties / tokenBudget / description

Added value: +"Token budget for the run; string id or object."

addedInput schema / properties / tool / description
```
Added value: +"Tool call spec for the run."
```
addedInput schema / properties / url / description
```
Added value: +"Target URL for the run."
```

addedInput schema / properties / warrantTemplate / description

Added value: +"Warrant template to apply to the run; string id or object."

Changed4 schema fields changedNov 6, 2026
- addedInput schema / properties / chamberSeal
```
Added value: +{
+  "type": "object"
+}
```
- addedInput schema / properties / depotStore
```
Added value: +{
+  "type": "object"
+}
```
- addedInput schema / properties / membership
```
Added value: +{
+  "type": "object"
+}
```
- addedInput schema / properties / riderPaidCall
```
Added value: +{
+  "type": "object"
+}
```
Changed1 schema field changedNov 6, 2026
- addedInput schema / properties / tokenBudget
```
Added value: +{
+  "type": "object"
+}
```

Changed20 schema fields changedNov 5, 2026

addedInput schema / properties / agent

Added value: +{
+  "type": [
+    "string",
+    "object"
+  ]
+}

addedInput schema / properties / asyncRun
```
Added value: +{
+  "type": "object"
+}
```

addedInput schema / properties / audit

Added value: +{
+  "type": [
+    "string",
+    "object"
+  ]
+}

addedInput schema / properties / conductorReview
```
Added value: +{
+  "type": "object"
+}
```

addedInput schema / properties / conductorTask

Added value: +{
+  "type": [
+    "string",
+    "object"
+  ]
+}

addedInput schema / properties / depotBilling
```
Added value: +{
+  "type": "object"
+}
```
addedInput schema / properties / depotReceipt
```
Added value: +{
+  "type": "object"
+}
```
addedInput schema / properties / dispute
```
Added value: +{
+  "type": "object"
+}
```
addedInput schema / properties / mcpTool
```
Added value: +{
+  "type": "object"
+}
```
addedInput schema / properties / message
```
Added value: +{
+  "type": "object"
+}
```
addedInput schema / properties / ops
```
Added value: +{
+  "type": "object"
+}
```
addedInput schema / properties / payout
```
Added value: +{
+  "type": "object"
+}
```
addedInput schema / properties / privateBench
```
Added value: +{
+  "type": "object"
+}
```

addedInput schema / properties / reputation

Added value: +{
+  "type": [
+    "string",
+    "object"
+  ]
+}

addedInput schema / properties / sandbox
```
Added value: +{
+  "type": "object"
+}
```

addedInput schema / properties / sku

Added value: +{
+  "type": [
+    "string",
+    "object"
+  ]
+}

addedInput schema / properties / solana
```
Added value: +{
+  "type": "object"
+}
```

addedInput schema / properties / standingRider

Added value: +{
+  "type": [
+    "string",
+    "object"
+  ]
+}

addedInput schema / properties / tool
```
Added value: +{
+  "type": "object"
+}
```

addedInput schema / properties / warrantTemplate

Added value: +{
+  "type": [
+    "string",
+    "object"
+  ]
+}

AddedNov 4, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is known. The description still adds concrete behavioral context beyond them: "no disk, no network, nothing is charged or started" and the fact that a quote and settlement preview are returned, which tells the agent a plan never commits money. It stops short of describing failure modes for an invalid run shape.

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

Conciseness4/5

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

Front-loaded with purpose, then behavior, then routing, with no repeated or filler sentences. The eight-name subsystem enumeration and the jargon-heavy stage names are dense but do communicate validation breadth, so the cost is minor rather than fatal.

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 35-parameter tool with zero required fields, the description covers what it does, what it returns, that nothing is charged or started, and how it relates to the run and context siblings. It could go further on how to know which optional stage fields to supply, but no output schema is needed since return contents are summarized.

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. The description earns above that by explaining the gating rule for the many optional stage inputs: any optional stage "whose spec field is present" is validated, and "action" determines which stages the plan includes. That is real selection semantics the schema cannot express on its own.

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?

"Plan one Agent Commerce Network (ACN) run without executing it" gives a specific verb (plan, without executing) plus a concrete resource (an ACN run), and names the exact validation surface (Rider, Warrant, Tollkeeper, Quikgater, PCC, AWLpay, PSI, Conductor). It is clearly distinguishable from the sibling spl_agentic_run, which actually executes.

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?

States both routing rules explicitly: "Use to dry-run a run before spl_agentic_run" and "use spl_agentic_context to shrink the context a run will carry." Both the when and the named alternatives are given, leaving little to inference.

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

All Slid Phi Labs 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.

Resources

Need Help?