Skip to main content
Glama
Sign In
MCP Events Bridge

MCP Events Bridge

Official
by hookdeck
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

list_events

Read-only

Lists past events newest first from Hookdeck Event Gateway, optionally filtered by event name and received time, so you can review what already happened.

Instructions

List past events, newest first by timestamp, from every source or for one event name, read from Hookdeck Event Gateway. Each has the eventId, name, timestamp and data its delivery has. Use it to look back at what already happened; to follow new events, use wait_for_event or poll_events, and for one event you have the id of, get_event. It reads each source's requests newest first until it has limit events, reading at most 500 per source, so with name on a busy source where few requests are that event it can return fewer than exist. Events Event Gateway no longer keeps aren't listed. An unknown name is an error; for the names, see list_sources or events/list.

Input Schema

NameRequiredDescriptionDefault
nameNoAn event name, such as resend.email.received. Omit for every source.
limitNoAt most this many events (default 20, at most 100).
sinceNoOnly events Event Gateway received at or after this time, in ISO 8601, e.g. 2026-11-04T09:00:00Z. It compares received time, not the event's timestamp.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.8.2
    • addedInput schema / properties / limit / description
      Added value: +"At most this many events (default 20, at most 100)."
    • changedInput schema / properties / name / description
      Previous value: -"An event name, such as resend.email.received"New value: +"An event name, such as resend.email.received. Omit for every source."
    • addedInput schema / properties / since / description
      Added value: +"Only events Event Gateway received at or after this time, in ISO 8601, e.g. 2026-11-04T09:00:00Z. It compares received time, not the event's timestamp."
  2. First observedv0.8.1

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, so the description does not need to restate safety. It instead adds non-obvious traits: per-source reads capped at 500, a limit that can therefore return fewer events than exist, retention limits on old events, and an error for unknown names. The only gap is no mention of what the returned payload looks like in aggregate, which is less critical for a list 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?

Purpose and ordering are front-loaded, then usage routing, then caveats, so the structure is sound. The single long paragraph with several chained clauses is dense, but almost every sentence carries information the agent needs.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a three-parameter list tool with no output schema, it covers ordering, scope, payload fields (eventId, name, timestamp, data), truncation behavior, retention, and the unknown-name error. Nothing needed to call it correctly or interpret results is missing.

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 the baseline is 3. The description goes beyond the schema by explaining how limit interacts with per-source reading and by warning that an unknown name is an error rather than an empty result, which changes how an agent should interpret an empty response.

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 opens with a specific verb and resource ('List past events'), its ordering ('newest first by timestamp'), and its scope ('from every source or for one event name'), plus the backing system (Hookdeck Event Gateway). This is enough to separate it from get_event, poll_events and wait_for_event without reading any schema.

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

Usage Guidelines5/5

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

It gives an explicit when-to-use ('look back at what already happened') and names two alternatives by function: wait_for_event and poll_events for following new events, get_event for a single known id. Exclusions are stated so the agent can route correctly.

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