Decision Anchor

propose_bilateral

Use when two agents need to fix a shared boundary: both sides must agree before the boundary is anchored. Essential for payment splits, task delegation, or any joint commitment between agents. Propose a bilateral agreement to another agent: creates a DD with declaration_mode 'bilateral' and waits for counterparty acceptance.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`auth_token`	No	Your DA agent auth token. Optional when this connection already carries one (Authorization: Bearer header on the remote server, or DA_AUTH_TOKEN for a local stdio server); an explicit value takes precedence.
`request_id`	No	Unique idempotency key for this request. Auto-generated if omitted.
`decision_at`	No	Optional: the time your agent itself decided, ISO 8601. The server normalizes it to UTC and that normalized value enters the integrity hash. It must not be later than the anchoring time (400 DECISION_AT_IN_FUTURE). Omit it and no decision time is recorded.
`access_class`	No	Optional: read-access class for the record
`dd_unit_type`	No	Decision unit type	single
`parent_dd_id`	No	Parent DD ID for lineage tracking
`decision_type`	Yes	Decision type
`selection_scope`	No	Optional: declared scope of the selection
`selection_state`	No	Selection state	SELECTED
`delegation_state`	No	Optional: delegation responsibility state (DAC add 0/10/30)
`payment_signature`	No	Optional x402 payment payload (base64), required only for paid calls. Omit it on the first call: the tool returns the payment challenge. Sign that challenge with your own wallet, then call this tool again with identical arguments plus this field. Decision Anchor never holds your key and never signs on your behalf.
`ee_retention_period`	No	How long the record is retained. indefinite is declared but not currently available: selecting it is rejected with 403.	medium
`origin_context_type`	Yes	Origin context
`decision_action_type`	Yes	Action type
`counterparty_agent_id`	Yes	The agent_id of the counterparty you are proposing to
`ee_direct_access_quota`	No	Direct access quota (omit to use the server config default)
`ee_direct_access_period`	No	Direct access period (e.g., 30d)	30d
`ee_responsibility_scope`	No	Responsibility scope	standard
`content_disclosure_scope`	No	Optional: external exposure scope (DAC add 0/15/40)
`ee_disclosure_format_policy`	No	Disclosure format	internal
`ee_integrity_verification_level`	No	Verification rigor	basic

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedSep 19, 2026

changedInput schema / properties / auth_token / description

Previous value: -"Your DA agent auth token"New value: +"Your DA agent auth token. Optional when this connection already carries one (Authorization: Bearer header on the remote server, or DA_AUTH_TOKEN for a local stdio server); an explicit value takes precedence."

changedInput schema / required

Previous value: -[
-  "auth_token",
-  "counterparty_agent_id",
-  "decision_type",
-  "decision_action_type",
-  "origin_context_type"
-]New value: +[
+  "counterparty_agent_id",
+  "decision_type",
+  "decision_action_type",
+  "origin_context_type"
+]

Changed1 schema field changedAug 25, 2026

changedInput schema / properties / ee_retention_period / description

Previous value: -"How long the record is retained (indefinite requires an active indefinite-retention subscription; otherwise 403)"New value: +"How long the record is retained. indefinite is declared but not currently available: selecting it is rejected with 403."

Changed2 schema fields changedAug 25, 2026

addedInput schema / properties / decision_at

Added value: +{
+  "description": "Optional: the time your agent itself decided, ISO 8601. The server normalizes it to UTC and that normalized value enters the integrity hash. It must not be later than the anchoring time (400 DECISION_AT_IN_FUTURE). Omit it and no decision time is recorded.",
+  "type": "string"
+}

removedInput schema / properties / excluded_option_count

Removed value: -{
-  "description": "Optional: number of options excluded when deciding (integer >= 0)",
-  "minimum": 0,
-  "type": "integer"
-}

Changed6 schema fields changedAug 20, 2026

changedInput schema / properties / access_class / description

Previous value: -"Optional — read-access class for the record"New value: +"Optional: read-access class for the record"

changedInput schema / properties / content_disclosure_scope / description

Previous value: -"Optional — external exposure scope (DAC add 0/15/40)"New value: +"Optional: external exposure scope (DAC add 0/15/40)"

changedInput schema / properties / delegation_state / description

Previous value: -"Optional — delegation responsibility state (DAC add 0/10/30)"New value: +"Optional: delegation responsibility state (DAC add 0/10/30)"

changedInput schema / properties / ee_retention_period / description

Previous value: -"How long the record is retained (indefinite requires an active indefinite-retention subscription — otherwise 403)"New value: +"How long the record is retained (indefinite requires an active indefinite-retention subscription; otherwise 403)"

changedInput schema / properties / excluded_option_count / description

Previous value: -"Optional — number of options excluded when deciding (integer >= 0)"New value: +"Optional: number of options excluded when deciding (integer >= 0)"

changedInput schema / properties / selection_scope / description

Previous value: -"Optional — declared scope of the selection"New value: +"Optional: declared scope of the selection"

Changed1 schema field changedJul 26, 2026

addedInput schema / properties / payment_signature

Added value: +{
+  "description": "Optional x402 payment payload (base64), required only for paid calls. Omit it on the first call: the tool returns the payment challenge. Sign that challenge with your own wallet, then call this tool again with identical arguments plus this field. Decision Anchor never holds your key and never signs on your behalf.",
+  "type": "string"
+}

Changed2 schema fields changedJul 24, 2026
- removedInput schema / properties / ee_direct_access_quota / default
```
Removed value: -5
```
- changedInput schema / properties / ee_direct_access_quota / description
```
Previous value: -"Direct access quota"New value: +"Direct access quota (omit to use the server config default)"
```

Changed11 schema fields changedJul 12, 2026

addedInput schema / properties / access_class

Added value: +{
+  "description": "Optional — read-access class for the record",
+  "enum": [
+    "self_direct",
+    "ara_only",
+    "internal_only"
+  ],
+  "type": "string"
+}

addedInput schema / properties / content_disclosure_scope

Added value: +{
+  "description": "Optional — external exposure scope (DAC add 0/15/40)",
+  "enum": [
+    "owner",
+    "external",
+    "public"
+  ],
+  "type": "string"
+}

changedInput schema / properties / decision_action_type / description

Previous value: -"Action type (e.g., execute, agree)"New value: +"Action type"

addedInput schema / properties / decision_action_type / enum

Added value: +[
+  "execute",
+  "hold",
+  "reject",
+  "depend",
+  "approve"
+]

changedInput schema / properties / decision_type / description

Previous value: -"Decision type (e.g., external_interaction)"New value: +"Decision type"

addedInput schema / properties / decision_type / enum

Added value: +[
+  "internal_service",
+  "external_interaction",
+  "self_attestation"
+]

addedInput schema / properties / delegation_state

Added value: +{
+  "description": "Optional — delegation responsibility state (DAC add 0/10/30)",
+  "enum": [
+    "none",
+    "partial",
+    "full"
+  ],
+  "type": "string"
+}

addedInput schema / properties / excluded_option_count

Added value: +{
+  "description": "Optional — number of options excluded when deciding (integer >= 0)",
+  "minimum": 0,
+  "type": "integer"
+}

changedInput schema / properties / origin_context_type / description

Previous value: -"Origin context (e.g., external, hybrid)"New value: +"Origin context"

addedInput schema / properties / origin_context_type / enum

Added value: +[
+  "internal",
+  "external",
+  "self",
+  "mixed"
+]

addedInput schema / properties / selection_scope

Added value: +{
+  "description": "Optional — declared scope of the selection",
+  "enum": [
+    "single_target",
+    "multi_target",
+    "chain_scope",
+    "global"
+  ],
+  "type": "string"
+}

Changed3 schema fields changedJul 12, 2026

changedInput schema / properties / ee_retention_period / description

Previous value: -"How long the record is retained"New value: +"How long the record is retained (indefinite requires an active indefinite-retention subscription — otherwise 403)"

changedInput schema / properties / ee_retention_period / enum

Previous value: -[
-  "short",
-  "medium",
-  "long"
-]New value: +[
+  "short",
+  "medium",
+  "long",
+  "extreme_long",
+  "indefinite"
+]

changedInput schema / properties / selection_state / enum

Previous value: -[
-  "SELECTED",
-  "DEFERRED",
-  "REJECTED"
-]New value: +[
+  "SELECTED",
+  "REJECTED",
+  "ABORTED",
+  "SILENT",
+  "NON_DECISION"
+]

AddedApr 12, 2026

TDQS

A3.9/5.0

Behavior3/5

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

With no annotations provided, the description carries the full behavioral burden. It discloses meaningful behavior: creates a bilateral declaration and waits for counterparty acceptance, implying a blocking/synchronization aspect. However, it does not mention auth requirements, failure modes, timeouts, or what happens on rejection, leaving notable gaps.

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?

Three sentences, all informative and front-loaded: first the when, then the examples, then the exact mechanism. There is no filler, repetition of schema details, or unnecessary context.

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?

The description explains the core purpose and high-level flow adequately, and the schema covers all parameter semantics. However, there is no output schema and the description does not describe the response format, timeout behavior, or how acceptance/rejection is surfaced, which is a meaningful gap for a complex 21-parameter tool.

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 parameters are already well documented and the description does not need to repeat them. The description adds context about the tool's purpose but no additional parameter-level meaning; the baseline 3 applies.

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 states a specific action—propose a bilateral agreement to another agent—and explains the resource created (a DD with declaration_mode 'bilateral') and the behavior (waits for counterparty acceptance). It clearly differentiates this from single-agent decision tools like create_decision and confirm_decision by emphasizing the shared-boundary, both-must-agree context.

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 opens with explicit when-to-use guidance: 'Use when two agents need to fix a shared boundary' and gives concrete examples like payment splits and task delegation. It does not explicitly state when not to use it or name alternative tools, so it stops short of a 5.

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

All Decision Anchor 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.

propose_bilateral

Input Schema

Schema Changelog

TDQS

Glama MCP Gateway

Resources