a2a2p — Agent-to-Agent-to-Physical

prepare_domain_solutioning_case

Prepare a synchronous, deterministic, privacy-minimized engineering case for a compatible domain-intelligence system. Use it when intake_classification is capability_concept or assembly_or_system and mechanism selection or decomposition is required, or when a complete single-part intent has no specifications and review offers the design_brief continuation. The case preserves requester facts, deterministic evidence, screening state, unknowns, and a versioned candidate-output contract while removing design-file URLs, bytes, contact fields, and callback routes. This operation does not call deb8stack or any model, choose a mechanism, validate a proposal, store a request, contact a supplier, or grant quote, order, payment, or fabrication authority.

Input Schema

TableJSON Schema

Name	Required	Description
`intent`	No	Layer 1 — the problem. What the physical matter needs to DO. Use this for intent-driven requests where the agent describes purpose and a2a2p recommends solutions.
`contact`	No	Optional email or callback endpoint for quote delivery.
`deadline`	No	Required delivery date or timeframe. Maps to intent.timeline.
`quantity`	No	Number of units needed. Maps to intent.quantity.
`budget_usd`	No	Approximate budget in USD. Maps to intent.budget_envelope.
`constraints`	No	Hard constraints: tolerances, certifications, materials to avoid, size/weight limits. Maps to intent.functional_requirements.
`requirement`	No	Plain-language description of the physical need. Maps to intent.purpose. Include function, dimensions, materials, load/performance requirements, environment, and interfaces where known.
`callback_url`	No	Optional HTTPS URL. When the quote is ready, a2a2p POSTs it as JSON to this URL.
`specification`	No	Layer 2 — the solution. What the physical matter IS. Populate what is known. Precise specifications produce faster, tighter quotes. Controlled vocabularies are preferred but open values are accepted.
`business_context`	No	Optional business requirements (expected volumes, cost targets, ROI constraints). If provided, the quote includes a business case.
`rejected_alternatives`	No	Options already considered and ruled out. Prevents re-suggesting and builds the learning corpus.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`next`	Yes
`safety`	Yes
`contract`	Yes
`authority`	Yes
`activation`	Yes
`provenance`	Yes
`case_digest`	Yes
`requirement`	Yes
`requested_work`	Yes
`expected_result`	Yes
`contract_version`	Yes
`deterministic_evidence`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 1, 2026

changedInput schema / properties / specification / properties / process / enum

Previous value: -[
-  "cnc_milling",
-  "cnc_turning",
-  "fdm_3d_print",
-  "sla_3d_print",
-  "sls_3d_print",
-  "sheet_metal",
-  "casting",
-  "injection_molding",
-  "extrusion"
-]New value: +[
+  "cnc_milling",
+  "cnc_turning",
+  "fdm_3d_print",
+  "sla_3d_print",
+  "sls_3d_print",
+  "sheet_metal",
+  "laser_cutting",
+  "casting",
+  "injection_molding",
+  "extrusion"
+]

Changed1 schema field changedAug 25, 2026

added

Input schema / properties / intent / properties / functional_requirements / properties / load_case / properties / allowable_shear_stress_mpa

Added value: +{
+  "description": "Optional requester-supplied transverse-shear design allowable; evaluated independently and never inferred from handbook data.",
+  "exclusiveMinimum": 0,
+  "type": "number"
+}

Changed5 schema fields changedAug 25, 2026
- changedInput schema / properties / intent / properties / purpose / description
```
Previous value: -"What the physical matter needs to accomplish (one line minimum, required)."New value: +"What the physical matter needs to accomplish (one non-whitespace line minimum, required)."
```
- addedInput schema / properties / intent / properties / purpose / minLength
```
Added value: +1
```
- addedInput schema / properties / intent / properties / purpose / pattern
```
Added value: +"\\S"
```
- addedInput schema / properties / requirement / minLength
```
Added value: +1
```
- addedInput schema / properties / requirement / pattern
```
Added value: +"\\S"
```
Changed27 schema fields changedAug 22, 2026
- addedOutput schema / $defs / candidate / properties / evidence_refs / items / additionalProperties
```
Added value: +true
```
- addedOutput schema / $defs / candidate / properties / evidence_refs / items / properties
```
Added value: +{
+  "kind": {
+    "maxLength": 5000,
+    "minLength": 1,
+    "type": "string"
+  },
+  "path": {
+    "maxLength": 5000,
+    "minLength": 1,
+    "type": "string"
+  }
+}
```
- addedOutput schema / $defs / candidate / properties / evidence_refs / items / required
```
Added value: +[
+  "kind",
+  "path"
+]
```
- addedOutput schema / $defs / candidate / properties / evidence_refs / minItems
```
Added value: +1
```
- addedOutput schema / $defs / candidate / properties / functional_decomposition / items / additionalProperties
```
Added value: +true
```
- addedOutput schema / $defs / candidate / properties / functional_decomposition / items / properties
```
Added value: +{
+  "function": {
+    "maxLength": 5000,
+    "minLength": 1,
+    "type": "string"
+  },
+  "part": {
+    "maxLength": 5000,
+    "minLength": 1,
+    "type": "string"
+  }
+}
```
- addedOutput schema / $defs / candidate / properties / functional_decomposition / items / required
```
Added value: +[
+  "function",
+  "part"
+]
```
- addedOutput schema / $defs / candidate / properties / functional_decomposition / maxItems
```
Added value: +100
```
- addedOutput schema / $defs / candidate / properties / rejected_alternatives / items / additionalProperties
```
Added value: +true
```
- addedOutput schema / $defs / candidate / properties / rejected_alternatives / items / properties
```
Added value: +{
+  "mechanism": {
+    "maxLength": 5000,
+    "minLength": 1,
+    "type": "string"
+  },
+  "reason": {
+    "maxLength": 5000,
+    "minLength": 1,
+    "type": "string"
+  }
+}
```
- addedOutput schema / $defs / candidate / properties / rejected_alternatives / items / required
```
Added value: +[
+  "mechanism",
+  "reason"
+]
```
- addedOutput schema / $defs / candidate / properties / tradeoffs / items / additionalProperties
```
Added value: +true
```
- addedOutput schema / $defs / candidate / properties / tradeoffs / items / properties
```
Added value: +{
+  "benefit": {
+    "maxLength": 5000,
+    "minLength": 1,
+    "type": "string"
+  },
+  "choice": {
+    "maxLength": 5000,
+    "minLength": 1,
+    "type": "string"
+  },
+  "cost": {
+    "maxLength": 5000,
+    "minLength": 1,
+    "type": "string"
+  }
+}
```
- addedOutput schema / $defs / candidate / properties / tradeoffs / items / required
```
Added value: +[
+  "choice",
+  "benefit",
+  "cost"
+]
```
- addedOutput schema / $defs / candidate / properties / validation_plan / items / additionalProperties
```
Added value: +true
```
- addedOutput schema / $defs / candidate / properties / validation_plan / items / properties
```
Added value: +{
+  "criterion": {
+    "maxLength": 5000,
+    "minLength": 1,
+    "type": "string"
+  },
+  "test": {
+    "maxLength": 5000,
+    "minLength": 1,
+    "type": "string"
+  }
+}
```
- addedOutput schema / $defs / candidate / properties / validation_plan / items / required
```
Added value: +[
+  "test",
+  "criterion"
+]
```
- changedOutput schema / $defs / result / properties / contract_version / const
```
Previous value: -"0.2.0-draft"New value: +"0.3.0-draft"
```
- addedOutput schema / $defs / result / properties / dissent / items / additionalProperties
```
Added value: +true
```
- addedOutput schema / $defs / result / properties / dissent / items / properties
```
Added value: +{
+  "candidate_id": {
+    "maxLength": 5000,
+    "minLength": 1,
+    "type": "string"
+  },
+  "concern": {
+    "maxLength": 5000,
+    "minLength": 1,
+    "type": "string"
+  }
+}
```
- addedOutput schema / $defs / result / properties / dissent / items / required
```
Added value: +[
+  "candidate_id",
+  "concern"
+]
```
- addedOutput schema / $defs / result / properties / dissent / maxItems
```
Added value: +100
```
- addedOutput schema / $defs / result / properties / recommendation / properties / overturn_if / items / maxLength
```
Added value: +5000
```
- addedOutput schema / $defs / result / properties / recommendation / properties / overturn_if / items / minLength
```
Added value: +1
```
- addedOutput schema / $defs / result / properties / recommendation / properties / overturn_if / items / type
```
Added value: +"string"
```
- changedOutput schema / contract_version
```
Previous value: -"0.2.0-draft"New value: +"0.3.0-draft"
```
- changedOutput schema / properties / contract_version / const
```
Previous value: -"0.2.0-draft"New value: +"0.3.0-draft"
```
AddedAug 21, 2026

TDQS

A4.1/5.0

Behavior5/5

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

No annotations are provided, so the description carries the full behavioral burden, and it does so richly. It declares the operation is synchronous, deterministic, and privacy-minimized; specifies what data is preserved (requester facts, deterministic evidence, screening state, unknowns, versioned candidate-output contract) and what is removed (design-file URLs, bytes, contact fields, callback routes); and explicitly disclaims calling deb8stack or any model, choosing mechanisms, validating proposals, storing requests, contacting suppliers, or granting commercial authority.

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 a dense single paragraph, but it front-loads the core purpose and follows immediately with usage conditions. Every sentence appears to add behavioral or routing information, though the long negation clause is somewhat run-on. It is appropriately sized for a complex, high-stakes tool but could be more scannable.

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 large nested input schema and the presence of an output schema, the description need not explain return values. It covers behavioral traits, privacy handling, usage conditions, and non-actions thoroughly. The main remaining gap is explicit routing to sibling alternatives for adjacent cases, which would make the definition more complete for agent selection.

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?

Schema description coverage is 100%, so the input schema already documents all 11 parameters, including nested intent, specification, and functional_requirements fields. The description does not add parameter-level meaning, syntax, or mapping guidance beyond what the schema provides. Under the rubric, a baseline of 3 is appropriate when the schema does the heavy lifting.

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 states a specific verb and resource: 'Prepare a ... engineering case for a compatible domain-intelligence system.' It distinguishes the tool through detailed intake conditions (capability_concept, assembly_or_system, single-part intent with no specifications) rather than naming sibling alternatives directly. The purpose is clear but somewhat jargon-heavy and does not explicitly differentiate itself from similarly named sibling 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 provides explicit when-to-use conditions: for capability_concept or assembly_or_system intake with mechanism selection or decomposition, and for a complete single-part intent with no specifications when review offers the design_brief continuation. It also lists many operations that this tool does NOT perform, such as choosing a mechanism, validating proposals, storing requests, or contacting suppliers. However, it never names an alternative sibling tool to use instead, which prevents a top score.

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

All a2a2p — Agent-to-Agent-to-Physical tools Inspect

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.