Skip to main content
Glama

Update an alert

update_alert
DestructiveIdempotent

Updates an alert by public id. Only the fields passed are changed, and each one overwrites the previous setting for every member of a shared alert. Does not use credits. Same fields as create_alert, including the share block {mode, userIds, optOutUserIds}. Any member of a shared alert may edit it. enrichContacts true or false turns contact lookup on or off for future runs (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. filters.leadTypes (for example ["private","public"]) widens an alert past private leads. Confirm with the user first.

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": {
      "alertId": "<alertId>"
    },
    "name": "update_alert"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNo1–255 characters.
shareNoTeam sharing. Any member of a shared alert may read, edit, run and delete it. Sharing requires a paid plan.
activeNo
notifyNo
alertIdYesThe planned-project alert's public id ("alr_…"), from list_alerts or create_alert. Permit alert ids ("palr_…") go to the permit alert tools.
cadenceNoDefaults to weekly.
filtersNoThe same filter vocabulary as get_projects, as a JSON object — integer geo ids from list_locations, project-type values from get_project_types. At least one filter is required. An alert delivers private leads by default; put leadTypes (e.g. ["private","public"]) inside filters to widen it, exactly as on get_projects.
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

A4.1/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true, idempotentHint=true and openWorldHint=true, so the safety bar is lower, yet the description still adds genuine behavior: partial-overwrite semantics, that a field change propagates to every member of a shared alert, that the call consumes no credits, and that notify destinations are stored but not sent. The credit cost of enrichContacts (1 credit per project where a contact is found, paid plan or trial required) is a useful non-obvious cost disclosure. It stops short of saying what a failed or partially-applied update looks like.

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 most important fact, partial update by public id, is front-loaded and nothing is filler. The paragraph is dense, though, with several unrelated concerns (sharing, credits, notify, filters) packed into consecutive sentences, which makes it slightly harder to scan than a short bulleted or segmented layout would be.

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 9-parameter mutation tool with nested objects, no output schema and destructive annotations, the description covers the risky surfaces: overwrite scope, shared-alert propagation, credit costs, external notification storage, and a confirmation prompt. Remaining gaps are minor — no statement of the response shape or of what happens when an update is rejected (e.g. outsider user ids, though the schema handles that).

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?

With schema coverage at 78%, the schema already documents most parameters, but the description still adds meaning the schema does not carry: the credit implications of enrichContacts, that notify.emailTo/webhookUrl are external destinations that are saved rather than dispatched, and that filters.leadTypes widens an alert beyond private leads. These are behavioral semantics rather than restatements, so it beats the baseline 3.

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 tied to an identifier ('Updates an alert by public id') and immediately scopes it as a partial update ('Only the fields passed are changed'). It also anchors itself to a sibling by field vocabulary ('Same fields as create_alert'), so an agent can distinguish it from create_alert and the permit-alert variants without reading the schema.

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

Usage Guidelines3/5

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

Gives real operating context: any member of a shared alert may edit it, and the user should be confirmed with first before enabling enrichContacts or widening leadTypes. However, it never explicitly routes the agent between this tool and its siblings (create_alert vs update_permit_alert vs update_preferences), leaving that inference to the reader.

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