Skip to main content
Glama

get_signal_events

Read-only

Read what signals detected (created with create_signal): new posts, comments, reactions, profile views and connection changes, one page at a time. Always pass since – the nextSince of your previous call – to read only what is new. Without since the tool reads the last 24 hours; pass an older since only when you need older events (they are kept 90 days). Returns { since, events, hasMore, nextSince }: since is the moment the page starts after; the page holds the earliest events recorded after it, listed newest first; nextSince is the newest detectedAt in the page. When hasMore is true, call again with since = nextSince for the next page – nothing is skipped or repeated. On a busy account narrow the read with signalId, signalType or eventType. Process each event once by its id. Every event carries signalId, signalType, label, type and detectedAt (when the check recorded it, not when it happened on LinkedIn), plus its subject: post (postPublished, postFound), postUrl and comment (commentAdded), postUrl and reaction (reactionAdded), viewer (profileViewed), or personUrn and personUrl (connectionAccepted, connectionAdded, connectionRequestReceived).

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_signal_events"
  }
}

Input Schema

NameRequiredDescriptionDefault
sinceNoISO 8601 timestamp: return events recorded after it (e.g., '2026-10-12T16:40:00.000Z'). Pass the nextSince of your previous call. Defaults to 24 hours ago.
signalIdNoOptional. Only events of this signal.
eventTypeNoOptional. Only events of this type.
signalTypeNoOptional. Only events of signals of this type.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is carried structurally; the description's added value is in the 90-day retention window, the at-least-once-to-exactly-once processing hint ("process each event once by its id"), and the warning that detectedAt is check time, not the LinkedIn event time. That is meaningful context beyond annotations, though filtering does not appear to reduce credit for this — it is solid but the description remains silent on rate limits and failure modes. With annotations covering most of the safety bar, the extra operational detail on retention and detectedAt semantics fits a 3–4 band.

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?

Front-loaded with purpose, then usage, then return shape — a logical order with no filler sentences. The single dense paragraph packs a lot of inline enumeration (event-to-subject mappings), which is information an agent needs but could be more scannable.

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 takes on the burden of describing the return shape and does so fully: the four top-level fields, page ordering (earliest after since, newest first), nextSince derivation, and the per-event fields including the discriminator-to-subject mapping. For a paginated read with four optional params, nothing an agent needs to call it correctly 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 still earns credit by explaining the causal chain between parameters — since comes from the prior call's nextSince, and signalId/signalType/eventType are narrowing filters to use when the account is busy. It stops short of adding format or syntax detail beyond what the schema's enum and ISO-8601 examples already give.

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?

Opens with a specific verb and resource ("Read what signals detected") and immediately names the sibling that produces those signals (create_signal), so an agent can place it in the workflow without opening a schema. It also enumerates the event categories it surfaces, which distinguishes it from the signal-management siblings.

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?

Gives explicit when-to guidance for the only real decision point: always pass since = the previous call's nextSince; absent since it reads the last 24 hours; use an older since only for events up to 90 days back. It also covers the pagination loop (hasMore → call again with since = nextSince, nothing skipped or repeated) and prescribes narrowing by signalId/signalType/eventType on busy accounts.

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.