Skip to main content
Glama

Create an alert

create_alert

Creates a recurring alert. Writing the alert does not use credits. Credits apply when a run delivers records. preview_alert returns the credit quote for the first run. Requires name and filters, the same fields as get_projects. Optional share block {mode, userIds, optOutUserIds}; sharing requires a paid plan. enrichContacts: true adds contact lookup on each run and costs 1 credit per project where a contact is found, on a paid plan or trial. Optional notify.emailTo (up to 5 extra addresses) and notify.webhookUrl save destinations outside this account. This call stores them and does not send. Delivers private leads by default. leadTypes inside filters (for example ["private","public"]) widens that set. Confirm with the user first: the name, the place, and the size floor.

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": {
      "name": "<name>",
      "filters": "<filters>"
    },
    "name": "create_alert"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesThe alert's name.
shareNoTeam sharing. Any member of a shared alert may read, edit, run and delete it. Sharing requires a paid plan.
activeNo
notifyNo
cadenceNoDefaults to weekly.
filtersYesAt least one filter, in the same vocabulary as get_projects — integer geo ids from list_locations, project-type values from get_project_types. Private leads by default; add leadTypes (e.g. ["private","public"]) inside this object to change the view.
enrichContactsNoFind Contact Info on every run: each run looks up developer emails and phones on the records it delivered BEFORE notifying, then get_alert_matches with include "contacts" returns them, best contacts first. 1 credit per project the first time a contact is found, nothing otherwise. Needs a paid plan or live trial. Confirm with the user before turning it on.
maxRecordsPerRunNoCap on records (= credits) one run may deliver.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only say this is a non-read-only, open-world, non-idempotent create; the description goes far beyond by explaining the credit model (no charge on write, charge at delivery time, per-project contact cost), plan gating for sharing and enrichment, and that notify destinations are stored but no message is sent. It also discloses that the alert is private by default and how leadTypes widens the set. That is exactly the kind of consequence information the annotations cannot carry.

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 is front-loaded and nearly every clause carries new information (costs, plan gates, confirmation). Some phrasing is compressed to the point of ambiguity, notably "the place, and the size floor," which reads as an internal shorthand rather than a clear instruction.

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 a create tool with no output schema, the description covers cost, permissions, privacy defaults, and pre-call confirmation well. It never states what the call returns (an alert object or id) that the agent would need to feed into run_alert or get_alert, and it leaves cadence/active defaults entirely to the schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With schema coverage at 75%, the description still adds substantial meaning: it explains that filters share the get_projects vocabulary, that leadTypes inside filters changes the default private view, the shape and paid-plan constraint of the share block, and the cost/timing semantics of enrichContacts plus its effect on get_alert_matches. This is cost and side-effect meaning the schema does not encode.

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 first sentence states a specific verb and resource ("Creates a recurring alert") and immediately positions it against a sibling ("preview_alert returns the credit quote for the first run"). An agent can tell this apart from update_alert, run_alert, and preview_alert 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 Guidelines5/5

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

It routes the agent to preview_alert for a credit quote before committing, states preconditions for optional behavior (sharing and enrichContacts both require a paid plan or trial), and mandates user confirmation of name, place, and size floor before calling. The when-to-use path and the prerequisite checks are explicit rather than inferred.

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.

Resources