Skip to main content
Glama

Robyn — Gasless Cross-Chain for AI Agents

by io.github.ox31461

Submit your signed intent (relayer pays the gas)

robyn_submit

Relay an intent you already signed. The relayer broadcasts it and fronts all network gas; your account needs no native token. Build permit2 from robyn_prepare: sign its signRequest.eip712 payload (canonical Permit2 domain + PermitTransferFrom/TokenPermissions types) and pass the OBJECT below - not a bare signature string. The signed spender must be the relayer from signRequest.spender, otherwise the permit cannot be redeemed. Supply idempotencyKey so a retry after a timeout cannot double-spend. TO REHEARSE WITHOUT BROADCASTING set dryRun:true — it returns {status:"DRY", broadcast:false, wouldSend} and moves nothing, on EVERY corridor. Do NOT assume that omitting a live flag means dry: that holds on the float lane and the non-EVM legs, but the EVM-to-EVM path ignores it and BROADCASTS.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
amountYes
dryRunNotrue = rehearse only: returns {status:"DRY", broadcast:false, wouldSend} and broadcasts NOTHING, on every corridor. Use this to preview before committing.
permit2YesPermit2 SignatureTransfer object - NOT a bare signature string
toChainYes
toTokenYes
fromChainYes
fromTokenYes
toAddressYes
idempotencyKeyNoany unique string; makes retries safe

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed1 schema field changed
    • addedInput schema / properties / dryRun
      Added value: +{
+  "description": "true = rehearse only: returns {status:\"DRY\", broadcast:false, wouldSend} and broadcasts NOTHING, on every corridor. Use this to preview before committing.",
+  "type": "boolean"
+}
  2. Changed5 schema fields changed
    • addedInput schema / properties / permit2 / additionalProperties
      Added value: +false
    • changedInput schema / properties / permit2 / description
      Previous value: -"the signature produced from signRequest"New value: +"Permit2 SignatureTransfer object - NOT a bare signature string"
    • addedInput schema / properties / permit2 / properties
      Added value: +{
+  "deadline": {
+    "description": "the deadline from signRequest.eip712.value.deadline",
+    "type": "string"
+  },
+  "nonce": {
+    "description": "the nonce from signRequest.eip712.value.nonce",
+    "type": "string"
+  },
+  "owner": {
+    "description": "address that signed the permit",
+    "type": "string"
+  },
+  "permitted": {
+    "additionalProperties": false,
+    "properties": {
+      "amount": {
+        "description": "exact base-unit amount (signRequest.amount)",
+        "type": "string"
+      },
+      "token": {
+        "description": "ERC-20 being permitted (signRequest.tokenAddress)",
+        "type": "string"
+      }
+    },
+    "required": [
+      "token",
+      "amount"
+    ],
+    "type": "object"
+  },
+  "signature": {
+    "description": "0x… signature over signRequest.eip712",
+    "type": "string"
+  }
+}
    • addedInput schema / properties / permit2 / required
      Added value: +[
+  "owner",
+  "permitted",
+  "nonce",
+  "deadline",
+  "signature"
+]
    • changedInput schema / properties / permit2 / type
      Previous value: -"string"New value: +"object"
  3. Added

TDQS

A4.5/5.0
Behavior5/5

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

With no annotations, the description carries full behavioral burden. It discloses that the relayer fronts gas, the signed spender must match the relayer, and the critical caveat that omitting a live flag may still broadcast on the EVM-to-EVM path. It also explains dryRun return values and idempotencyKey semantics, providing rich behavioral context.

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?

The description is dense but well-organized, with the main action up front, then permit2 construction, safety warnings, and a critical corridor-specific caveat. Every sentence serves a purpose, though the all-caps warnings and repeated emphasis make it slightly longer than strictly necessary. It earns a 4 for effectiveness despite minor verbosity.

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?

The description covers the tool's core workflow, permit2 construction, gas sponsorship, dryRun behavior, and idempotency. Given the complexity (nested permit2 object, dryRun variations) and absent output schema, this is quite complete. However, the normal (non-dryRun) return value is never described, which is a notable gap for a submission tool.

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 description coverage is only 33%, so the description must compensate. It adds crucial meaning for permit2 (explicitly stating it is an object, not a bare signature, and how to build it) and idempotencyKey (prevents double-spend on retry). However, basic params like fromChain/toChain and amount receive no additional explanation beyond their names, leaving some ambiguity.

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 opens with a specific verb and resource: 'Relay an intent you already signed.' It clearly distinguishes this as the submission step after robyn_prepare, distinct from related tools like robyn_quote or robyn_preflight. The scope (broadcast signed intent, relayer pays gas) is explicit.

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?

The description provides clear usage context: build permit2 from robyn_prepare, sign the eip712 payload, and pass the object. It also warns about dryRun behavior and idempotency. However, it does not explicitly mention when not to use this tool vs. alternatives, so it stops short of a 5.

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

All Robyn — Gasless Cross-Chain for AI Agents toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.6/5.0
Disambiguation2/5

Many tools have overlapping purposes, such as robyn_quote, robyn_prepare, robyn_settle, robyn_cross_chain, robyn_plan, robyn_preflight, and robyn_preflight_full, all involving routing or quoting. Although descriptions are detailed, the high number of subtly different tools makes selection error-prone.

Naming Consistency5/5

All tools follow a consistent <prefix>_<verb/noun> pattern, with robyn_ and null_ as clear category prefixes. Verbs like prepare, submit, verify and nouns like quote, plan, mesh are highly predictable throughout.

Tool Count2/5

With 70 tools, the count far exceeds the 25+ heavy threshold. While the service scope is broad (payments, messaging, netting, Plus, yield, etc.), many tools could be merged or tiered, making the set feel overly large and burdensome for an agent.

Completeness4/5

The surface covers the full lifecycle from quoting, planning, submitting, verifying, auditing to messaging, custody, yield, and mandates, plus sandbox, lint, and recipes. A few advanced operations like cancellation or revocation are missing, but no critical gaps remain.

Resources