Skip to main content
Glama
phamviet86

codex-hermes-a2a-bridge

by phamviet86
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

hermes_chat

Destructive

Start or continue a Hermes conversation via A2A, returning a durable bridge task and context mapping for tracking requests across sessions.

Instructions

Start or continue a Hermes conversation; returns a durable bridge task and A2A context mapping.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeNoauto waits briefly, sync waits, async returns earlyauto
originNo
messageYesUser request for Hermes
profileNoHermes profile; v0.1 supports default onlydefault
task_idNo
timeoutNoAbsolute task/stream timeout in seconds
context_idNoExisting A2A contextId; normally reuse the returned value
idempotency_keyNoClient key used to deduplicate exactly matching submissions
conversation_keyNoStable Codex conversation identifier

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.5.0
    • addedInput schema / properties / origin
      Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": {
+        "type": "string"
+      },
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Origin"
+}
    • addedInput schema / properties / task_id
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Task Id"
+}
  2. First observedv0.1.1

TDQS

B3.2/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true, openWorldHint=true and idempotentHint=false, so the safety profile is covered externally. The description usefully adds that a durable task and A2A context mapping are returned (relevant for continuation), but it never explains the non-idempotent/destructive posture or how mode affects blocking behavior.

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?

A single sentence, front-loaded with the action and followed by the return-value clause; nothing is padded. It is dense with domain jargon ('A2A context mapping', 'bridge task') that is never unpacked, which slightly undercuts clarity.

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?

With a rich 9-parameter schema, full annotations and an output schema, the description does not need to carry everything. Still, for a conversation-continuation tool it omits the practical guidance an agent most needs: how the returned task/context IDs feed back into subsequent calls.

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 78%, so the schema already documents mode, profile, timeout, context_id, idempotency_key and conversation_key. The description's phrase 'A2A context mapping' loosely echoes context_id but adds no syntax, defaults, or reuse rules beyond what the schema states.

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?

States a specific verb and resource ('Start or continue a Hermes conversation') and adds a distinctive output promise ('durable bridge task and A2A context mapping'). It does not, however, name or contrast any sibling (e.g. hermes_task_wait, hermes_contexts), so an agent must infer where this sits in the family.

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?

'Start or continue' implies a lifecycle but gives no explicit when-to-use guidance: nothing says when to reuse task_id/context_id versus starting fresh, nor when to prefer sync over async. No alternatives or exclusions are named.

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

Deploy Server

Other Tools