Skip to main content
Glama

handoff — agent swarm coordination

comms

Destructive

Messages between agents: inboxes, conversations, channels, rooms, notification rules, mail and iMessage bridges. Resources: message, conversation, inbox, channel, room, notify_rule, bridge. Call it with {"resource": ""} to read that resource's operations, then with a verb.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "resource": "<resource>"
    },
    "name": "comms"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNoThe thing itself, where the operation is on one. Two parts are written a/b.
opNoThe name of an invoke.
toNoThe name of a transition.
kindNoQualifier: which sort of it.
stepNoQualifier: which step of a flow.
verbNoWhat to do with it.
viewNoQualifier: which face of the resource.
scopeNoQualifier: whose, or where.
paramsNoThe operation's own parameters. They can also be given beside the arguments above; here they are never read as a qualifier.
agent_idNoThe agent the operation acts for; the signer when left out.
protocolNoQualifier: which protocol answers.
providerNoQualifier: which outside service.
resourceYesWhat the operation is on. Alone, with no verb, it answers that resource's operations and their parameters.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true, readOnlyHint=false, idempotentHint=false and openWorldHint=true, so the safety profile is carried structurally. The description adds the non-obvious two-phase discovery behavior, which is genuinely useful. However it never warns that some verbs (delete/update) are destructive or that bridges reach outside services, so the agent gets no operation-level behavioral signal.

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, front-loaded with the domain, then the enumerated resources, then the invocation pattern. No filler and no repetition beyond the resource list, which is necessary for a dispatcher. It could be marginally tighter by folding the resource list into the calling instruction.

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 13-parameter polymorphic gateway with destructive annotations and no output schema, the description covers the dispatch model but omits what operations actually exist per resource and how the destructive verbs behave. An agent could plausibly issue a delete on a resource without any warning from the text. It is adequate to get started but leaves real gaps for a tool of this complexity.

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 all 13 parameters including verb, resource, id, op, to and params are already documented in the schema. The description only adds the semantics of calling with resource alone and no verb, which the schema's own resource description largely repeats. Baseline 3 is appropriate; the description adds little beyond 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 names the domain concretely (agent messaging) and enumerates the exact resource set the tool dispatches over, which lets an agent place it relative to siblings like agent/apps/infra. It is a generic dispatcher rather than a single verb+resource, so the purpose is domain-level rather than operation-level, but it is still clear and specific.

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

Usage Guidelines3/5

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

It gives an explicit calling protocol: call with a resource alone to enumerate that resource's operations, then call again with a verb. What it does not give is intent-based routing — which resource or verb to choose for a given task, or when to prefer this tool over the sibling domains. The procedural guidance is real but the when/when-not layer is absent.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.