A2A Artifact Handoff

compile_handoff

Compile source-agent outputs into a receiver-ready handoff package.

The input schema declares the exact source-output, receiver-contract, and handoff-context fields. The tool selects and validates required deliverables and returns either a portable package or actionable unmet requirements.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`ttl_hours`	No
`source_outputs`	Yes
`handoff_context`	Yes
`receiver_contract`	Yes

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

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

Changed10 schema fields changedAug 5, 2026

addedInput schema / $defs

Added value: +{
+  "ContractConstraints": {
+    "examples": [
+      {
+        "maxFileBytes": 100000,
+        "requireSha256": true
+      }
+    ],
+    "properties": {
+      "maxFileBytes": {
+        "anyOf": [
+          {
+            "minimum": 1,
+            "type": "integer"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "description": "Optional maximum size in bytes for each delivered artifact.",
+        "title": "Maxfilebytes"
+      },
+      "requireSha256": {
+        "default": true,
+        "description": "Require SHA-256 integrity metadata for delivered artifacts.",
+        "title": "Requiresha256",
+        "type": "boolean"
+      }
+    },
+    "title": "ContractConstraints",
+    "type": "object"
+  },
+  "HandoffContext": {
+    "properties": {
+      "assumptions": {
+        "items": {
+          "type": "string"
+        },
+        "title": "Assumptions",
+        "type": "array"
+      },
+      "decisions": {
+        "items": {
+          "type": "string"
+        },
+        "title": "Decisions",
+        "type": "array"
+      },
+      "destinationAgent": {
+        "anyOf": [
+          {
+            "maxLength": 200,
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "title": "Destinationagent"
+      },
+      "objective": {
+        "maxLength": 2000,
+        "minLength": 1,
+        "title": "Objective",
+        "type": "string"
+      },
+      "sourceAgent": {
+        "anyOf": [
+          {
+            "maxLength": 200,
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "title": "Sourceagent"
+      },
+      "status": {
+        "default": "completed",
+        "maxLength": 80,
+        "title": "Status",
+        "type": "string"
+      },
+      "unresolvedIssues": {
+        "items": {
+          "type": "string"
+        },
+        "title": "Unresolvedissues",
+        "type": "array"
+      }
+    },
+    "required": [
+      "objective"
+    ],
+    "title": "HandoffContext",
+    "type": "object"
+  },
+  "OutputRequirement": {
+    "description": "One deliverable expected by the receiving agent.",
+    "examples": [
+      {
+        "acceptedMediaTypes": [
+          "text/markdown"
+        ],
+        "filename": "report.md",
+        "id": "report",
+        "required": true
+      },
+      {
+        "acceptedMediaTypes": [
+          "text/csv"
+        ],
+        "filename": "evidence.csv",
+        "id": "evidence",
+        "required": true,
+        "requiredCsvColumns": [
+          "channel",
+          "score",
+          "evidence"
+        ]
+      },
+      {
+        "acceptedMediaTypes": [
+          "application/json"
+        ],
+        "filename": "summary.json",
+        "id": "summary",
+        "required": true,
+        "requiredJsonKeys": [
+          "recommendation",
+          "confidence"
+        ]
+      }
+    ],
+    "properties": {
+      "acceptedMediaTypes": {
+        "description": "Media types accepted for this deliverable, for example text/markdown, text/csv, or application/json.",
+        "items": {
+          "type": "string"
+        },
+        "minItems": 1,
+        "title": "Acceptedmediatypes",
+        "type": "array"
+      },
+      "description": {
+        "anyOf": [
+          {
+            "maxLength": 500,
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "title": "Description"
+      },
+      "filename": {
+        "anyOf": [
+          {
+            "maxLength": 200,
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "description": "Filename required by the receiving agent.",
+        "title": "Filename"
+      },
+      "id": {
+        "description": "Stable requirement identifier. Use the matching source output id when known; use filename only for the delivered filename.",
+        "maxLength": 80,
+        "minLength": 1,
+        "title": "Id",
+        "type": "string"
+      },
+      "required": {
+        "default": true,
+        "description": "Whether this deliverable is mandatory.",
+        "title": "Required",
+        "type": "boolean"
+      },
+      "requiredCsvColumns": {
+        "description": "Use only when acceptedMediaTypes contains text/csv. Leave empty for Markdown, text, JSON, images, and other media types.",
+        "items": {
+          "type": "string"
+        },
+        "title": "Requiredcsvcolumns",
+        "type": "array"
+      },
+      "requiredJsonKeys": {
+        "description": "Use only when acceptedMediaTypes contains application/json. Leave empty for Markdown, text, CSV, images, and other media types.",
+        "items": {
+          "type": "string"
+        },
+        "title": "Requiredjsonkeys",
+        "type": "array"
+      }
+    },
+    "required": [
+      "id",
+      "acceptedMediaTypes"
+    ],
+    "title": "OutputRequirement",
+    "type": "object"
+  },
+  "ReceiverContract": {
+    "description": "Machine-readable input contract declared by the receiving agent.",
+    "properties": {
+      "constraints": {
+        "$ref": "#/$defs/ContractConstraints",
+        "description": "Runtime constraint values. Provide requireSha256 and optionally maxFileBytes; do not copy JSON Schema definitions into this field."
+      },
+      "contractVersion": {
+        "default": "0.1",
+        "title": "Contractversion",
+        "type": "string"
+      },
+      "destinationCapability": {
+        "maxLength": 200,
+        "minLength": 1,
+        "title": "Destinationcapability",
+        "type": "string"
+      },
+      "requiredOutputs": {
+        "items": {
+          "$ref": "#/$defs/OutputRequirement"
+        },
+        "minItems": 1,
+        "title": "Requiredoutputs",
+        "type": "array"
+      }
+    },
+    "required": [
+      "destinationCapability",
+      "requiredOutputs"
+    ],
+    "title": "ReceiverContract",
+    "type": "object"
+  },
+  "SourceOutput": {
+    "description": "One output produced by the source agent.",
+    "properties": {
+      "content": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "title": "Content"
+      },
+      "contentBase64": {
+        "anyOf": [
+          {
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "title": "Contentbase64"
+      },
+      "filename": {
+        "maxLength": 200,
+        "minLength": 1,
+        "title": "Filename",
+        "type": "string"
+      },
+      "id": {
+        "maxLength": 80,
+        "minLength": 1,
+        "title": "Id",
+        "type": "string"
+      },
+      "mediaType": {
+        "maxLength": 120,
+        "minLength": 3,
+        "title": "Mediatype",
+        "type": "string"
+      },
+      "role": {
+        "anyOf": [
+          {
+            "maxLength": 80,
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ],
+        "default": null,
+        "title": "Role"
+      }
+    },
+    "required": [
+      "id",
+      "filename",
+      "mediaType"
+    ],
+    "title": "SourceOutput",
+    "type": "object"
+  }
+}

addedInput schema / properties / handoff_context / $ref
```
Added value: +"#/$defs/HandoffContext"
```

removedInput schema / properties / handoff_context / anyOf

Removed value: -[
-  {
-    "additionalProperties": true,
-    "type": "object"
-  },
-  {
-    "type": "string"
-  }
-]

removedInput schema / properties / handoff_context / title
```
Removed value: -"Handoff Context"
```
addedInput schema / properties / receiver_contract / $ref
```
Added value: +"#/$defs/ReceiverContract"
```

removedInput schema / properties / receiver_contract / anyOf

Removed value: -[
-  {
-    "additionalProperties": true,
-    "type": "object"
-  },
-  {
-    "type": "string"
-  }
-]

removedInput schema / properties / receiver_contract / title
```
Removed value: -"Receiver Contract"
```
addedInput schema / properties / source_outputs / items / $ref
```
Added value: +"#/$defs/SourceOutput"
```
removedInput schema / properties / source_outputs / items / additionalProperties
```
Removed value: -true
```
removedInput schema / properties / source_outputs / items / type
```
Removed value: -"object"
```

AddedAug 4, 2026

TDQS

C2.9/5.0

Behavior3/5

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

There are no annotations, so the description carries the full burden. It does disclose a meaningful behavior: 'selects and validates required deliverables and returns either a portable package or actionable unmet requirements.' This tells the agent that validation can fail and the output may be a requirements list rather than a package. However, it does not mention side effects, permissions, or whether source outputs are left intact.

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?

Three sentences with no filler; the primary action is front-loaded. The middle sentence about the input schema is somewhat meta but compact. Overall it is concise and readable, though the second sentence could be considered redundant since the schema is visible to the agent.

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

Completeness2/5

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

For a tool with four parameters, three required nested objects, and no annotations, the description is thin. It does not explain how to construct source_outputs, what a receiver_contract is, or what handoff_context must contain. An output schema exists, so return values are covered, but correct invocation of a contract-driven tool would need more context than this description provides.

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?

Schema description coverage is 0% for top-level parameters, so the description should compensate. It only says the schema declares 'source-output, receiver-contract, and handoff-context fields' without explaining what they mean, how they relate, or what values are expected. This adds little beyond pointing back at the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb–resource pair: 'Compile source-agent outputs into a receiver-ready handoff package.' This clearly identifies the operation and its product. It does not explicitly contrast itself with sibling tools inspect_handoff or prepare_artifact, so it misses the top score, but the compilation role is unmistakable.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is given about when to choose this tool over the siblings. The description implies a packaging scenario but does not state prerequisites, exclusions, or alternatives. With siblings like inspect_handoff and prepare_artifact present, the absence of routing guidance is a notable gap.

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

All A2A Artifact Handoff 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

B3.4/5.0

Disambiguation3/5

compile_handoff and prepare_artifact both produce transferable packages, which could cause confusion about which to use for a given handoff. inspect_handoff is clearly distinct, and tool descriptions help clarify the intended lifecycle stages, but the boundary between compiling and preparing remains somewhat fuzzy.

Naming Consistency4/5

compile_handoff and inspect_handoff follow a consistent verb_handoff pattern, but prepare_artifact breaks the pattern by changing the object and verb style. Overall the naming is readable and predictable despite the one deviation.

Tool Count5/5

Three tools is well-scoped for a focused artifact handoff server, covering compilation, inspection, and preparation without unnecessary bloat. Each tool addresses a distinct lifecycle stage.

Completeness4/5

The set covers the core handoff workflow: compile, inspect, and prepare artifacts for transfer. There is no explicit delivery or acceptance tool, but inspect_handoff returns an acceptance decision, so the lifecycle is reasonably complete with only minor gaps.

Resources

Need Help?