Skip to main content
Glama
Sign In
MCP Events Bridge

MCP Events Bridge

Official
by hookdeck
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

wait_for_event

Read-only

Blocks until new webhook events arrive after a cursor, returning them or an empty result at timeout; reuse the returned cursor to continue listening.

Instructions

Wait for the next events after your cursor, returning as soon as there are some, or with none after timeoutMs (default 45 s, at most 50 s). Without a cursor, waits for events from now on. Call it again with the cursor it returns to keep waiting; dedupe by eventId. Uses the same cursor as poll_events and events/poll.

Input Schema

NameRequiredDescriptionDefault
nameYesThe event type name, from list_sources (or events/list), such as github.issues
cursorNoThe cursor from your last call. Omit (or null) to start from now: the first call returns no events, only a cursor.
argumentsNoThe event type's arguments, as its inputSchema in list_sources (or events/list) describes them, e.g. { "repository": "owner/name", "actions": ["opened"] } for github.issues. An unknown argument or a wrong type is an error that lists the event type's arguments.
timeoutMsNoHow long to wait, in milliseconds (default 45000).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.10.0
    • changedInput schema / properties / arguments / description
      Previous value: -"Filters, as the event's inputSchema in events/list describes, e.g. { \"symbol\": \"AAPL\" }"New value: +"The event type's arguments, as its inputSchema in list_sources (or events/list) describes them, e.g. { \"repository\": \"owner/name\", \"actions\": [\"opened\"] } for github.issues. An unknown argument or a wrong type is an error that lists the event type's arguments."
    • changedInput schema / properties / name / description
      Previous value: -"The event name, from events/list, such as fills.order.filled"New value: +"The event type name, from list_sources (or events/list), such as github.issues"
  2. First observedv0.8.1

TDQS

A4.3/5.0
Behavior5/5

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

Annotations only declare readOnlyHint=true, so the description carries the behavioral burden and does so thoroughly: it discloses that the call blocks until events arrive or the timeout elapses, the default (45 s) and hard cap (50 s), and the non-obvious first-call behavior where no cursor means no events and only a cursor is returned. It also flags the dedupe-by-eventId requirement, which an agent would otherwise get wrong on repeated calls.

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?

Four short sentences with zero filler, front-loaded with the wait/timeout contract before the cursor and dedupe mechanics. Every sentence contributes an operational fact 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?

With no output schema, the description compensates by explaining what comes back (events plus a cursor) and how to continue the loop. Combined with a fully documented schema for the nested arguments parameter, an agent has everything needed to call this correctly and repeatedly.

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%, including the nested arguments object with a worked github.issues example, so the schema already does the heavy lifting. The description restates the timeout default and cap and reinforces cursor semantics, but adds no meaning beyond what the schema documents. Baseline 3 is appropriate.

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 opens with a precise verb and resource plus return semantics: 'Wait for the next events after your cursor, returning as soon as there are some, or with none after timeoutMs.' An agent immediately knows this is a long-poll wait rather than a fetch. It references poll_events only to note a shared cursor, not to explain how the two differ in behavior, so sibling differentiation is implied rather than stated.

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 concrete operating guidance: omit the cursor to start from now, call again with the returned cursor to keep waiting, and dedupe by eventId. That covers the iterative loop pattern well. It does not state when to choose this over poll_events despite naming it, leaving the polling-vs-waiting decision to inference.

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