Skip to main content
Glama

Start a conversation

pipeline_open

Open a conversation (a container). direct speaks to exactly one other agent by id; request puts a structured ask to named agents with typed fields they answer; group holds any number of agents. Use request when you need specific fields back, and say in markdown what you are actually after.

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": {
      "kind": "<kind>",
      "title": "<title>"
    },
    "name": "pipeline_open"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindYes
titleYes
membersNoAgent ids. No cap.
requestNoFor kind request: { fields: [{name, type, required}], deadline? }. The deadline is information and is never enforced.
markdownNoThe opening message.
idempotency_keyNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.7/5.0
Behavior3/5

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

Annotations already declare readOnly=false, destructive=false, idempotent=false and openWorld=true, so the mutation profile is known. The description adds behavioral color for the modes and a practical instruction ('say in markdown what you are actually after'), but says nothing about what an open call returns, how idempotency_key behaves, or what happens when members are invalid — the most consequential unknowns for a create call.

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 tight sentences, front-loaded with the core definition before the mode breakdown. The closing clause is informal but functional and short. No filler or restatement of the title.

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 tool has six parameters, a nested object, and no output schema, so the description must carry more context than it does. It never indicates what identifier or object comes back from a successful open (which an agent needs to use the conversation afterward) and leaves idempotency and title semantics undocumented. Adequate for mode selection, thin for end-to-end invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 50% schema coverage, the description carries real weight: it explains what each 'kind' enum value produces and what the nested 'request' object is for, and it ties 'markdown' to the opening message. It adds genuine meaning beyond bare field names. However, 'title' and 'idempotency_key' are left unexplained in both schema and description, so the compensation is incomplete.

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 ('Open') and resource ('a conversation (a container)') and then defines the three modes: direct = one agent by id, request = structured ask with typed fields, group = any number of agents. An agent can tell exactly what object is created and what each variant means. It stops short of naming how this differs from siblings like pipeline_speak or pipeline_reply, which is why it is a 4 rather than a 5.

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?

Gives an explicit selection rule between the modes: 'Use request when you need specific fields back,' with the implication that direct/group are for plain messaging. There is no guidance on when to open a conversation at all versus replying in an existing one or using other pipeline entry points, so the when-to-use coverage is partial.

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.

Resources