Skip to main content
Glama

SignalRaven

by io.github.signalraven
OverviewDiscussionsAdmin

Monitor a person

monitor_person

Start monitoring one or more people by LinkedIn profile URL, or the person of an existing Person Intelligence snapshot (snapshotId; the first check then skips the month the snapshot already covered). The person is checked weekly for posts, reposts, comments and reactions that match your ICP; someone with nothing new is checked every two weeks, then monthly, and weekly again as soon as they do something. Each check costs 1 credit, plus 0.25 credit per item read and 1 credit per signal delivered. Monitored people are unlimited and are not counted against your source limit. SPENDS CREDITS on each weekly check. Returns the rows created and the inputs skipped with a reason (duplicate, invalid_format, already_active, conflict, ceiling_reached).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
inputsNoLinkedIn profile URLs (or /in/ slugs), up to 1000 per call. Ignored when snapshotId is given.
admitLevelNoWhat counts as a signal for this person. 2 (default): stated needs only — activity whose text states a need, pain or buying moment your product addresses. 3: also topic interest — professional content about your category with no stated need, delivered as topic-interest signals (metadata.topicInterest true) with a strength floor of 5 instead of 8.
periodDaysNoHow long to monitor: 30, 90 or 180 days, or null for no end date. Default 90.
snapshotIdNoA Person Intelligence snapshot id from your workspace; monitors that person.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
ctaNoPresent in sample mode: how to get live data.
dataYesThe result, or null when nothing matched.
modeYeslive: the caller's workspace. sample: illustrative data for accounts without an approved workspace.
noticeNoPresent in sample mode: explains that the data is illustrative.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / admitLevel
      Added value: +{
+  "description": "What counts as a signal for this person. 2 (default): stated needs only — activity whose text states a need, pain or buying moment your product addresses. 3: also topic interest — professional content about your category with no stated need, delivered as topic-interest signals (metadata.topicInterest true) with a strength floor of 5 instead of 8.",
+  "enum": [
+    2,
+    3
+  ],
+  "type": "integer"
+}
  2. Changed2 schema fields changed
    • changedInput schema / properties / inputs / description
      Previous value: -"LinkedIn profile URLs (or /in/ slugs), up to 100 per call. Ignored when snapshotId is given."New value: +"LinkedIn profile URLs (or /in/ slugs), up to 1000 per call. Ignored when snapshotId is given."
    • changedInput schema / properties / inputs / maxItems
      Previous value: -100New value: +1000
  3. Added

TDQS

A4.6/5.0
Behavior5/5

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

Goes well beyond the annotations by disclosing the cost model (1 credit per check, 0.25 per item read, 1 per delivered signal), the adaptive check cadence (weekly → biweekly → monthly → weekly), that monitored people don't count against source limits, and the exact skip reasons returned. This is precisely the mutation-cost and side-effect context an agent needs before spending credits.

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?

The action and both input modes are front-loaded, and every sentence carries usable information (cadence, credits, skip reasons). It is dense and reads as a single long block, which slightly hurts scanability, but there is no filler to cut.

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?

An output schema exists, so return formatting is handled elsewhere; the description still summarizes returns (created rows plus skipped inputs with reasons), and it covers cost, cadence, and lifetime semantics. Nothing an agent needs to invoke this spend-incurring tool 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, but the description adds semantics the schema does not carry — notably that snapshotId causes the first check to skip the already-covered month and that inputs is ignored when snapshotId is present. admitLevel and periodDays are left entirely to the well-documented schema.

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?

States a specific verb and resource ('Start monitoring one or more people') and enumerates the two mutually exclusive entry routes (LinkedIn profile URLs or a Person Intelligence snapshotId). An agent can immediately tell this is the create/enroll counterpart to stop_monitoring_person and update_person_monitoring without opening 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 Guidelines4/5

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

Explicitly disambiguates when to use each input mode, including the subtle detail that monitoring from a snapshotId skips the month already covered, plus which inputs are ignored in each case. It does not name any sibling alternative (e.g. run_person_intelligence for a one-off check) or state exclusions, so it falls short of a 5.

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

All SignalRaven toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources