Clarifo

create_automation_draft

Idempotent

Create a Clarifo Automate automation, switched off. Nothing runs and nothing is spent until it is activated (activate_automation after the user approves, or in Clarifo). Use when the user asks for recurring research, e.g. a weekly watchlist brief.

Show the user the returned summary (what, scope, schedule, timezone, next_run, folder) before offering to activate. kind=prompt reads only its watchlist (scope.company_count, scope.companies_sample): when the instructions name companies or a sector outside it, say which are not covered before offering to activate, and offer to add them to the watchlist (save_to_workspace) or a kind=reports automation with a sector, industry or market scope instead.

Args: name: Short name, up to 60 characters. idempotency_key: Optional; leave it out. Clarifo recognises a repeated identical request by its content. Give one only to retry this same request. kind: "prompt" answers instructions across the watchlist on a cadence; "reports" drafts a cited document for each newly reported company in scope. instructions: For kind=prompt, what to answer (10+ characters). cadence: For kind=prompt: daily, weekly (default), monthly, quarterly. scope_kind: For kind=reports: all, market, watchlist, sector, industry, releases. kind=prompt reads watchlists only (all or watchlist); the result's scope says how many companies that is. scope_value: Market, sector, or watchlist (portfolio) id; for kind=prompt a watchlist id, or empty for every watchlist in the workspace. folder: Workspace folder for the output. run_times: Times of day, "HH:MM" in 15-minute steps (up to 6). run_days: ISO weekdays, 1 = Monday. timezone_name: IANA zone, e.g. "Europe/Helsinki", "America/New_York". max_new_per_run: Documents per run at most (1-25). language: Output language for kind=prompt: en, fi, sv. workspace_id: A workspace the user owns; omit when they own one. template: Optional; the name (or id) of one of the user's report templates, made in Clarifo under Automate > Report templates: a company-report template for kind=reports, a portfolio-report template for kind=prompt. Omit for Clarifo's standard format. An unknown name returns the available ones.

Returns: {"status": "draft_created", "automation_id", "enabled": false, "what", "schedule", "timezone", "next_run", "activation_token", "review_url"} or {"error", "failure_kind"}.

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>"
    },
    "name": "create_automation_draft"
  }
}

Input Schema

Name	Required	Default
`kind`	No	prompt
`name`	Yes
`folder`	No	Auto-drafts
`cadence`	No
`language`	No	en
`run_days`	No
`template`	No
`run_times`	No
`scope_kind`	No	all
`scope_value`	No
`instructions`	No
`workspace_id`	No
`timezone_name`	No
`idempotency_key`	No
`max_new_per_run`	No

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 9, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=true, but the description adds the material point that nothing runs or is spent until activation, which is the fact that actually governs whether an agent should call this. It also refines the idempotency annotation ("Clarifo recognises a repeated identical request by its content") far beyond the bare hint, and notes the ownership prerequisite on workspace_id.

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 and safety, then clean Args/Returns sections; the dense paragraph on watchlist coverage is long but pays for itself in preventing a mis-scoped automation. Minor waste: the Returns block largely restates an output schema that already exists, which is redundant space on a 15-parameter tool.

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 15-parameter, high-complexity creation tool this covers everything an agent needs: default behaviour, the kind=prompt vs kind=reports branch, template resolution and its failure mode (unknown name returns available ones), and the activation handoff. The only redundancy is re-describing a return shape already captured by the output 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?

Schema description coverage is 0% across 15 parameters, so the description carries the full burden and does: it enumerates allowed values for kind, cadence, scope_kind, language, and timezone format, gives the 15-minute step rule for run_times, ISO weekday convention for run_days, the 1-25 bound for max_new_per_run, and the 60-character name limit. It also explains the cross-parameter coupling (scope_kind behaviour depends on kind) that no flat schema could express.

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 ("Create a Clarifo Automate automation") plus the decisive state detail ("switched off"). It immediately names the contrasting operation (activate_automation) so the agent can separate drafting from activating without inspecting either 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?

Gives an explicit trigger ("Use when the user asks for recurring research, e.g. a weekly watchlist brief") and a concrete alternative with its own condition (save_to_workspace to widen the watchlist, or a kind=reports automation with sector/industry/market scope). It also prescribes the post-call step (show summary, then offer activation), which is genuine routing guidance.

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

All Clarifo tools Inspect

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.