Skip to main content
Glama

AgentWork Outcomes

by io.github.mitchellOpZero
OverviewDiscussionsAdmin

Request an outcome

request_outcome

Find a reliable procurement plan for an outcome and return one retail quote for confirmation. This does not spend, post, purchase, or invoke anything.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
contextNoOptional non-secret context needed to plan the outcome.
outcomeNoThe complete outcome the caller wants.
deadlineNoOptional delivery deadline.
done_whenNoOptional observable completion criteria.
retry_gap_idNoRetry a previously recorded routing or scoping gap with fresh supply checks.
authority_scopesNoExplicit non-financial authority granted for this outcome. Quote confirmation grants spend only.
max_spend_microsNoOptional maximum retail spend in USDC micros. Zero permits only free routes.
repeat_of_outcome_idNoReuse a verified route where compatible. Supply a fresh outcome, done_when, inputs, and authority; previous values are never inherited.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • changedInput schema / oneOf
      Previous value: -[
-  {
-    "required": [
-      "outcome"
-    ]
-  },
-  {
-    "required": [
-      "retry_gap_id"
-    ]
-  },
-  {
-    "required": [
-      "repeat_of_outcome_id"
-    ]
-  }
-]New value: +[
+  {
+    "not": {
+      "anyOf": [
+        {
+          "required": [
+            "retry_gap_id"
+          ]
+        },
+        {
+          "required": [
+            "repeat_of_outcome_id"
+          ]
+        }
+      ]
+    },
+    "required": [
+      "outcome"
+    ]
+  },
+  {
+    "not": {
+      "anyOf": [
+        {
+          "required": [
+            "outcome"
+          ]
+        },
+        {
+          "required": [
+            "repeat_of_outcome_id"
+          ]
+        }
+      ]
+    },
+    "required": [
+      "retry_gap_id"
+    ]
+  },
+  {
+    "not": {
+      "required": [
+        "retry_gap_id"
+      ]
+    },
+    "required": [
+      "repeat_of_outcome_id"
+    ]
+  }
+]
    • changedInput schema / properties / max_spend_micros / description
      Previous value: -"Optional maximum retail spend in USDC micros."New value: +"Optional maximum retail spend in USDC micros. Zero permits only free routes."
    • changedInput schema / properties / max_spend_micros / minimum
      Previous value: -1New value: +0
    • changedInput schema / properties / repeat_of_outcome_id / description
      Previous value: -"Repeat a completed outcome through fresh supply checks and pricing."New value: +"Reuse a verified route where compatible. Supply a fresh outcome, done_when, inputs, and authority; previous values are never inherited."
  2. Changed1 schema field changed
    • addedInput schema / properties / authority_scopes
      Added value: +{
+  "description": "Explicit non-financial authority granted for this outcome. Quote confirmation grants spend only.",
+  "items": {
+    "enum": [
+      "read_public_data",
+      "contact_external_party",
+      "represent_requester",
+      "create_account",
+      "create_or_use_wallet",
+      "publish",
+      "use_private_data"
+    ],
+    "type": "string"
+  },
+  "type": "array",
+  "uniqueItems": true
+}
  3. First observed

TDQS

A4.4/5.0
Behavior5/5

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

The description explicitly states that the tool does not spend, post, purchase, or invoke anything. This is a strong disclosure of non-executing behavior, making the side effects clear even without 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 concise, consisting of two clear sentences that succinctly convey purpose and side effects. It is well-structured and free of unnecessary detail.

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 provides sufficient context about the tool's purpose and non-executing nature, but lacks details about the expected output format (the quote structure) or how to interpret the returned quote. Given the rich schema, this is a minor gap.

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?

The schema provides 100% coverage for all parameters, so the baseline is 3. The tool description adds no additional meaning beyond the schema, such as relationships between parameters or usage details for specific fields.

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 function: to find a reliable procurement plan and return a retail quote for confirmation. This distinguishes it from sibling tools like confirm_outcome, get_outcome, and resume_outcome, which handle confirmation, retrieval, and resumption respectively.

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 implies this tool is the initial step for requesting an outcome and obtaining a quote before confirmation. However, it does not explicitly state when to prefer this over confirm_outcome or resume_outcome, leaving some inference to the agent.

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

All AgentWork Outcomes toolsInspect
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