Skip to main content
Glama

Keep a search or question on a schedule

create_monitor

Keep a web search or an agent question and run it again on a schedule, each run compared with the last one that answered: new, dropped and moved results for a search, the answer's added, changed and removed values for a question. Use it when the person asks to keep watching, monitoring or tracking something on the web -- a brand's mentions, a ranking, a competitor's prices. To watch a whole site's pages use create_project; to ask once use search_web or run_agent. Inputs: kind 'search' with query (news=true for news results), or kind 'agent' with prompt and optional urls, schema and allowed_domains (omitted, it stays on the sites of urls, as run_agent does). schedule is hourly, daily or weekly. follow_rows=true follows a list answer record by record (read with get_monitor_rows). Cost: each run is charged as the search or agent run it is -- a results page 1 to 4 credits, an agent run up to max_credits -- and the first run starts now. max_credits_per_month skips runs once the month has spent that much. Effect: it answers with the monitor; list_monitors shows its runs. pause_monitor stops it. Needs write access; a read-only connection is refused with code 'read_only'.

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": {
      "kind": "<kind>",
      "schedule": "<schedule>"
    },
    "name": "create_monitor"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindYes'search' keeps a web search; 'agent' keeps a research question.
nameNoA display name; omit for the query or the prompt.
newsNokind 'search' only: true searches news results; default false.
urlsNokind 'agent' only: up to 20 absolute URLs it starts from.
queryNokind 'search' only: what to search for, as typed into a search engine.
promptNokind 'agent' only: the question, 1 to 10,000 characters.
schemaNokind 'agent' only: a JSON Schema (type object or array) for the answer.
scheduleYesHow often it runs again.
follow_rowsNokind 'agent' only: true follows a list answer record by record; default false.
max_creditsNokind 'agent' only: the most one run may spend, 1 to 100,000; omit for 2,000.
allowed_domainsNokind 'agent' only: sites it stays within; omitted, the sites of urls; [] any site.
max_credits_per_monthNoThe most its runs may spend in a calendar month, in credits; omit or 0 for no cap.

Output Schema

NameRequiredDescriptionDefault
idNoThe monitor's id, for list_monitors, pause_monitor and get_monitor_rows.
codeNoOnly on a failure: a machine-readable reason, e.g. read_only, validation, plan_limit or not_found.
kindNo'search' or 'agent'.
nameNoIts name; the query or the prompt unless one was given.
noteNoWhat happens next, or what was left out.
rowsNoWhen it follows its answer as records: {path, key, confirmAfter}.
errorNoOnly when the call failed: what went wrong, in words an assistant can act on.
budgetNo{perRun, perMonth} in credits; 0 is no cap.
detailNoOnly on a failure: the API's own wording, when the error was rephrased.
statusNo'active' or 'paused'. On an error, the HTTP status code.
lastRunNoIts latest run: {status, changed, summary, credits, refId}; refId is the search or agent run it made.
requestNoThe search or agent request it runs, in the API's names.
scheduleNo'hourly', 'daily' or 'weekly'.
nextRunAtNoWhen it runs next, ISO 8601; null while paused.
spentThisMonthNoWhat its runs cost this calendar month (UTC), in credits.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only declare the safety profile (readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false); the description adds substantial context beyond that: per-run credit cost with a range, the first run firing immediately on creation, the monthly budget cap silently skipping runs, and the write-access requirement with the specific 'read_only' error code. It also documents the downstream lifecycle (list_monitors shows runs, pause_monitor stops it, get_monitor_rows reads followed rows).

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?

Paragraphs are front-loaded and labeled (purpose, when-to-use, Inputs, Cost, Effect), so an agent can scan for the section it needs. It is dense rather than padded, though a few clauses (e.g. repeating read paths already implied by sibling names) could be trimmed without loss.

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?

For a 12-parameter creation tool with an output schema, the description covers what an agent still needs: cost model, immediate first run, budget-cap side effect, auth failure mode, and where to go next for results. Return values are correctly left to the output schema, so nothing material 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 already 100%, so baseline would be 3, but the description adds cross-parameter conditional logic the schema cannot express: kind 'search' pairs with query (plus news), kind 'agent' pairs with prompt and optional urls, schema and allowed_domains. It also documents the non-obvious inherited default that omitted allowed_domains stays on the sites of urls, as run_agent does, and routes follow_rows to get_monitor_rows.

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 ('Keep a web search or an agent question and run it again on a schedule') and immediately defines the differentiating behavior: each run is diffed against the last answering run, with named diff categories for search vs agent. That scope plus the contrast with create_project, search_web and run_agent lets an agent distinguish it from every sibling it could be confused with.

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 an explicit trigger ('when the person asks to keep watching, monitoring or tracking something on the web') with concrete examples (brand mentions, ranking, competitor prices), plus named alternatives with the conditions that select them: create_project for whole-site page watching, search_web or run_agent for a one-off. Both when-to-use and when-not-to-use are covered.

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.