AgentWork Outcome Router

resolve_blocker

Submit one real task your agent cannot finish. AgentWork immediately returns a private request ID and token before running supply discovery. Call get_blocker_resolution with those credentials to run or read privacy-safe discovery and obtain a current complete route or an honest no_credible_route. Save the token: it is returned only once. Discovery cannot invoke, procure, pay, post, or expose private context.

Input Schema

TableJSON Schema

Name	Required	Description
`context`	No	Authorized private or public references and context needed to route the work.
`request`	Yes	What the agent is trying to complete and what is blocking it.
`deadline`	No
`authority`	No	Actions AgentWork may take and actions that still require approval.
`escalation`	No	Structured agent-reported unfinished work requiring an explicit owner confirmation before any commercial offer.
`max_budget`	No
`preference`	No

Schema Changelog

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

Changed5 schema fields changedAug 18, 2026

removedInput schema / properties / escalation / properties / attempted_artifacts / items / additionalProperties
```
Removed value: -false
```

addedInput schema / properties / escalation / properties / attempted_artifacts / items / anyOf

Added value: +[
+  {
+    "additionalProperties": false,
+    "properties": {
+      "label": {
+        "maxLength": 100,
+        "minLength": 3,
+        "type": "string"
+      },
+      "sha256": {
+        "pattern": "^[a-f0-9]{64}$",
+        "type": "string"
+      }
+    },
+    "required": [
+      "label",
+      "sha256"
+    ],
+    "type": "object"
+  },
+  {
+    "additionalProperties": false,
+    "properties": {
+      "label": {
+        "maxLength": 100,
+        "minLength": 3,
+        "type": "string"
+      },
+      "public_url": {
+        "maxLength": 2048,
+        "pattern": "^https:\\/\\/(?![^/?#]*@)(?!(?:localhost|[^/?#]*\\.(?:local|internal|test)|\\d{1,3}(?:\\.\\d{1,3}){3})(?::\\d{1,5})?(?:\\/|$))(?=[A-Za-z0-9.-]*\\.[A-Za-z0-9.-]+(?::\\d{1,5})?(?:\\/|$))[A-Za-z0-9.-]+(?::\\d{1,5})?(?:\\/[^?#]*)?$",
+        "type": "string"
+      }
+    },
+    "required": [
+      "label",
+      "public_url"
+    ],
+    "type": "object"
+  }
+]

removedInput schema / properties / escalation / properties / attempted_artifacts / items / properties

Removed value: -{
-  "label": {
-    "maxLength": 100,
-    "minLength": 3,
-    "type": "string"
-  },
-  "public_url": {
-    "format": "uri",
-    "maxLength": 2048,
-    "type": "string"
-  },
-  "sha256": {
-    "pattern": "^[a-f0-9]{64}$",
-    "type": "string"
-  }
-}

removedInput schema / properties / escalation / properties / attempted_artifacts / items / required
```
Removed value: -[
-  "label"
-]
```
removedInput schema / properties / escalation / properties / attempted_artifacts / items / type
```
Removed value: -"object"
```

Changed1 schema field changedAug 18, 2026

addedInput schema / properties / escalation

Added value: +{
+  "additionalProperties": false,
+  "description": "Structured agent-reported unfinished work requiring an explicit owner confirmation before any commercial offer.",
+  "properties": {
+    "allowed_input_labels": {
+      "items": {
+        "maxLength": 100,
+        "minLength": 3,
+        "type": "string"
+      },
+      "maxItems": 12,
+      "type": "array"
+    },
+    "attempt_count": {
+      "maximum": 1000,
+      "minimum": 1,
+      "type": "integer"
+    },
+    "attempted_artifacts": {
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "label": {
+            "maxLength": 100,
+            "minLength": 3,
+            "type": "string"
+          },
+          "public_url": {
+            "format": "uri",
+            "maxLength": 2048,
+            "type": "string"
+          },
+          "sha256": {
+            "pattern": "^[a-f0-9]{64}$",
+            "type": "string"
+          }
+        },
+        "required": [
+          "label"
+        ],
+        "type": "object"
+      },
+      "maxItems": 10,
+      "minItems": 1,
+      "type": "array"
+    },
+    "done_when": {
+      "items": {
+        "maxLength": 500,
+        "minLength": 20,
+        "type": "string"
+      },
+      "maxItems": 10,
+      "minItems": 1,
+      "type": "array"
+    },
+    "elapsed_minutes": {
+      "maximum": 525600,
+      "minimum": 1,
+      "type": "integer"
+    },
+    "expected_artifact": {
+      "maxLength": 1000,
+      "minLength": 20,
+      "type": "string"
+    },
+    "material_constraints": {
+      "items": {
+        "maxLength": 500,
+        "minLength": 3,
+        "type": "string"
+      },
+      "maxItems": 10,
+      "type": "array"
+    },
+    "owner_feedback": {
+      "maxLength": 1000,
+      "minLength": 20,
+      "type": "string"
+    },
+    "requested_authority": {
+      "items": {
+        "enum": [
+          "read_public_data",
+          "use_owner_supplied_inputs",
+          "contact_supplier",
+          "procure_execution"
+        ],
+        "type": "string"
+      },
+      "maxItems": 4,
+      "type": "array"
+    },
+    "unresolved": {
+      "const": true,
+      "type": "boolean"
+    }
+  },
+  "required": [
+    "expected_artifact",
+    "attempted_artifacts",
+    "owner_feedback",
+    "unresolved",
+    "attempt_count",
+    "elapsed_minutes",
+    "done_when",
+    "material_constraints",
+    "allowed_input_labels",
+    "requested_authority"
+  ],
+  "type": "object"
+}

AddedAug 17, 2026

TDQS

A4.2/5.0

Behavior5/5

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

With no annotations provided, the description carries full responsibility for behavioral disclosure, and it delivers. It states that the tool returns a private request ID and token before running discovery, that the token is returned only once, and that discovery cannot invoke, procure, pay, post, or expose private context. This gives the agent a strong safety and side-effect profile.

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 three dense sentences with no filler. It front-loads the core purpose, then covers the immediate return value, the follow-up call, the one-time token warning, and the safety constraints. Every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with seven parameters, nested objects, no annotations, and no output schema, the description covers the high-level workflow and safety model but leaves gaps around how to populate optional parameters like deadline, max_budget, and preference, and what the exact response contract is. It is clear enough for a simple submission but not fully complete for a complex tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 57% description coverage, so some parameters are already documented, but the description adds almost no parameter-level meaning beyond implying that 'request' is the real task. It does not explain deadline, max_budget, preference, authority, context, or the complex escalation object, leaving the agent to infer their roles from the schema alone.

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: 'Submit one real task your agent cannot finish.' It clearly distinguishes this tool from get_blocker_resolution by explaining that resolve_blocker creates the request and returns credentials, while get_blocker_resolution consumes those credentials to run discovery. This leaves no ambiguity about what the tool is for.

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 an explicit condition for use ('your agent cannot finish' a real task) and prescribes the next step: call get_blocker_resolution with the returned credentials. It does not explicitly list when not to use this tool or mention sibling alternatives like search_services or select_blocker_offer, but the workflow is clear enough that an agent can route itself correctly.

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

All AgentWork Outcome Router tools Inspect

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

A3.5/5.0

Disambiguation3/5

Most tools are separated by lifecycle stage, and the descriptions are detailed, but resolve_blocker and request_outcome_execution both accept work the agent cannot complete, making their boundary subtle. get_blocker_resolution and get_outcome_execution are also both private status readers, so some overlap exists even though descriptions help.

Naming Consistency4/5

The set is mostly consistent with snake_case verb_noun names like search_work, select_blocker_offer, and report_blocker_outcome. buyer_capabilities is a bare noun phrase rather than a verb_noun, and submission verbs vary between resolve and request, but overall the naming remains predictable.

Tool Count5/5

Ten tools is well within the well-scoped range for a workflow server. Each tool supports the blocker lifecycle, execution status, or work/service discovery, and none feels gratuitous.

Completeness4/5

The core workflow is fully represented: resolve a blocker, discover routes, select an offer, execute, read evidence, and report outcomes. There is no explicit cancel or request-history tool, and some search/discovery tools are not tied to a follow-up action, but these are minor gaps rather than dead ends.

Resources

Need Help?