Skip to main content
Glama

Axiom Agentic Tools

by io.github.0xAxiom

Multi-Agent Workflow Designer

multi-agent-workflow-designer
Read-onlyIdempotent

Compose a directed acyclic graph of public x402, MCP, and A2A tools that achieves a stated agent goal. Returns step-by-step plan with tool slug, endpoint URL, protocol, inputs, dependencies, per-step cost and latency, total estimated cost, and an executable plan in either a2a-json-rpc or shell-curl form. Useful for autonomous agents that need to pick which paid tools to chain.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
goalYesPlain-English agent goal, e.g. 'sweep top 5 floor NFTs in collection X if contract is safe and gas is low'.
max_stepsNoCap on number of steps in the returned DAG.
budget_usdNoMaximum total spend across all chained tool calls. Steps over budget are pruned.
output_formatNoExecutable plan format. Defaults to a2a-json-rpc.
preferred_protocolsNoRestrict catalog selection to these protocols. Empty = all.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
goalYes
stepsYes
evidenceYes
fallbacksYes
generated_atYes
budget_statusYes
next_check_atNoISO 8601 timestamp suggesting when the caller should re-invoke this tool. Derived from the tool's recurringHint.intervalSeconds.
output_formatYes
total_cost_usdYes
executable_planYes
total_latency_ms_estimateYes

Schema Changelog

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

  1. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "additionalProperties": false,
+  "properties": {
+    "budget_status": {
+      "enum": [
+        "under_budget",
+        "no_budget_specified",
+        "pruned_to_budget",
+        "over_budget_unprunable"
+      ],
+      "type": "string"
+    },
+    "evidence": {
+      "additionalProperties": false,
+      "properties": {
+        "catalog_entries_considered": {
+          "minimum": 1,
+          "type": "integer"
+        },
+        "catalog_version": {
+          "minLength": 1,
+          "type": "string"
+        },
+        "matched_keywords": {
+          "items": {
+            "maxLength": 48,
+            "minLength": 1,
+            "type": "string"
+          },
+          "maxItems": 32,
+          "type": "array"
+        }
+      },
+      "required": [
+        "catalog_version",
+        "catalog_entries_considered",
+        "matched_keywords"
+      ],
+      "type": "object"
+    },
+    "executable_plan": {
+      "additionalProperties": false,
+      "properties": {
+        "format": {
+          "enum": [
+            "a2a-json-rpc",
+            "shell-curl"
+          ],
+          "type": "string"
+        },
+        "payload": {
+          "maxLength": 20000,
+          "minLength": 1,
+          "type": "string"
+        }
+      },
+      "required": [
+        "format",
+        "payload"
+      ],
+      "type": "object"
+    },
+    "fallbacks": {
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "for_step": {
+            "pattern": "^s[0-9]+$",
+            "type": "string"
+          },
+          "protocol": {
+            "enum": [
+              "x402",
+              "mcp",
+              "a2a",
+              "rest"
+            ],
+            "type": "string"
+          },
+          "reason": {
+            "maxLength": 200,
+            "minLength": 4,
+            "type": "string"
+          },
+          "tool_slug": {
+            "minLength": 1,
+            "type": "string"
+          },
+          "tool_url": {
+            "format": "uri",
+            "type": "string"
+          }
+        },
+        "required": [
+          "for_step",
+          "tool_slug",
+          "tool_url",
+          "protocol",
+          "reason"
+        ],
+        "type": "object"
+      },
+      "maxItems": 12,
+      "type": "array"
+    },
+    "generated_at": {
+      "format": "date-time",
+      "type": "string"
+    },
+    "goal": {
+      "minLength": 1,
+      "type": "string"
+    },
+    "next_check_at": {
+      "description": "ISO 8601 timestamp suggesting when the caller should re-invoke this tool. Derived from the tool's recurringHint.intervalSeconds.",
+      "format": "date-time",
+      "type": "string"
+    },
+    "output_format": {
+      "enum": [
+        "a2a-json-rpc",
+        "shell-curl"
+      ],
+      "type": "string"
+    },
+    "steps": {
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "category": {
+            "enum": [
+              "gas",
+              "safety",
+              "nft-market",
+              "wallet-risk",
+              "token-due-diligence",
+              "identity",
+              "narrative",
+              "influence",
+              "portfolio",
+              "tokenomics",
+              "indexer",
+              "block-explorer"
+            ],
+            "type": "string"
+          },
+          "cost_usd": {
+            "maximum": 1000,
+            "minimum": 0,
+            "type": "number"
+          },
+          "depends_on": {
+            "items": {
+              "pattern": "^s[0-9]+$",
+              "type": "string"
+            },
+            "maxItems": 11,
+            "type": "array"
+          },
+          "inputs": {
+            "type": "object"
+          },
+          "latency_ms": {
+            "maximum": 60000,
+            "minimum": 50,
+            "type": "integer"
+          },
+          "protocol": {
+            "enum": [
+              "x402",
+              "mcp",
+              "a2a",
+              "rest"
+            ],
+            "type": "string"
+          },
+          "rationale": {
+            "maxLength": 240,
+            "minLength": 4,
+            "type": "string"
+          },
+          "step_id": {
+            "pattern": "^s[0-9]+$",
+            "type": "string"
+          },
+          "tool_slug": {
+            "minLength": 1,
+            "type": "string"
+          },
+          "tool_url": {
+            "format": "uri",
+            "type": "string"
+          }
+        },
+        "required": [
+          "step_id",
+          "tool_slug",
+          "tool_url",
+          "protocol",
+          "category",
+          "inputs",
+          "depends_on",
+          "cost_usd",
+          "latency_ms",
+          "rationale"
+        ],
+        "type": "object"
+      },
+      "maxItems": 12,
+      "minItems": 1,
+      "type": "array"
+    },
+    "total_cost_usd": {
+      "maximum": 1000,
+      "minimum": 0,
+      "type": "number"
+    },
+    "total_latency_ms_estimate": {
+      "maximum": 600000,
+      "minimum": 50,
+      "type": "integer"
+    }
+  },
+  "required": [
+    "goal",
+    "steps",
+    "total_cost_usd",
+    "total_latency_ms_estimate",
+    "fallbacks",
+    "executable_plan",
+    "output_format",
+    "budget_status",
+    "evidence",
+    "generated_at"
+  ],
+  "type": "object"
+}
  2. First observed

TDQS

A4/5.0
Behavior3/5

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

Annotations already disclose readOnlyHint=true, destructiveHint=false, and idempotentHint=true, lowering the bar. The description adds useful context: it returns a step-by-step plan with cost/latency estimates and executable formats, and it restricts to 'public' tools. However, it doesn't go deeper into edge cases, such as pruning behavior or how it handles unavailable tools. It earns a solid 3 for adding some context without contradicting 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?

The description is two sentences: the first states the core action, the second details the return value and use case. It is front-loaded with the verb 'Compose' and includes no filler. Every sentence earns its place.

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?

Given the tool's moderate complexity (5 params, 1 required) and the presence of an output schema, the description provides a complete enough overview. It lists the key outputs (tool slug, endpoint URL, protocol, inputs, dependencies, costs, latency, executable plan) and mentions the supported protocols. It doesn't mention budget pruning defaults, but those are in the parameter descriptions. A 4 reflects that it is slightly incomplete for a planning tool but still sufficient.

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?

Input schema covers 100% of parameters with descriptions, so the baseline is 3. The tool description does not elaborate on individual parameters (goal, max_steps, budget_usd, etc.), but the schema already provides full semantics. The description adds no parameter-level detail beyond the schema, so a 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?

The description clearly states the tool's primary function: 'Compose a directed acyclic graph of public x402, MCP, and A2A tools that achieves a stated agent goal.' It specifies the resource (tools) and the action (compose a DAG), and distinguishes it from siblings by focusing on workflow composition rather than revenue, token strategy, or other single-purpose tools.

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 gives clear context: 'Useful for autonomous agents that need to pick which paid tools to chain.' This implies the tool's niche but doesn't explicitly mention when not to use it or name alternative tools. Since no exclusions are provided, it falls short of a 5 but is above a vague 3.

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

All Axiom Agentic Tools 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

A4.2/5.0
Disambiguation5/5

Each tool targets a distinct domain: revenue auditing, token strategy, grants, gas, security, workflow design, prediction markets, repo health, and wallet balances. No two tools have overlapping purposes, making selection unambiguous for an agent.

Naming Consistency4/5

All names use lowercase hyphenated format, but prefixes vary (agent-, base-, mcp-, etc.) and some are descriptive while others are domain-based. This is mostly consistent but lacks a uniform pattern like verb-noun.

Tool Count5/5

9 tools is well within the ideal range for a focused server. Each tool addresses a distinct need for autonomous agents on Base, and none feel redundant or unnecessary.

Completeness4/5

The set covers analysis, planning, and monitoring aspects well (revenue, token, grants, gas, security, workflow, odds, repo, portfolio). Missing execution-oriented tools like token deployment or transaction sending, but for an intelligence-focused suite, this is reasonable.

Resources