Skip to main content
Glama

publish_event

Publishes project events to the EVC Mesh event bus, including summaries and status updates, and can optionally persist key decisions as permanent memory.

Instructions

Publish an event to the event bus. event_type='summary' publishes a summary. Add memory={persist:true, key:'decision-name'} to also save as permanent memory. Replaces the deprecated publish_summary tool.

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": {
      "project_id": "<project_id>",
      "event_type": "<event_type>",
      "subject": "<subject>",
      "payload": "<payload>"
    },
    "name": "publish_event"
  }
}

Input Schema

NameRequiredDescriptionDefault
tagsNoEvent tags for filtering.
memoryNoOptional memory hint to persist alongside the event (e.g. key decisions, conventions).
payloadYesEvent payload as key-value pairs.
subjectYesEvent subject line.
task_idNoRelated task ID.
ttl_hoursNoTime-to-live in hours (default 24).
event_typeYesEvent type: summary, status_change, context_update, error, dependency_resolved, custom.
project_idYesProject ID.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.1

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare this is a non-readonly, non-destructive, non-idempotent write operation. The description adds useful behavioral context by explaining the summary event behavior and the memory persistence side effect, though it does not detail return behavior or event-bus delivery semantics.

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?

The description is three short sentences, front-loads the main action, and every sentence adds actionable information with no filler.

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?

For an 8-parameter write tool with full schema coverage and no output schema, the description covers the core action and the important memory side effect. Minor gaps remain around event-bus semantics and the exact effect of memory fields beyond the example.

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?

Schema coverage is 100%, so parameters are largely documented. The description still adds value by giving a concrete memory syntax example, 'memory={persist:true, key:"decision-name"}', which compensates for the schema's empty memory properties object.

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 uses a precise verb and resource: 'Publish an event to the event bus.' It also clarifies a special case ('event_type=summary') and explicitly distinguishes this tool from the deprecated publish_summary sibling.

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?

It gives clear context for publishing events and explains how to add memory persistence, while naming the deprecated alternative it replaces. It does not explicitly say when to use this instead of sibling tools such as post_project_update or remember.

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