Skip to main content
Glama

Run a ready-made recipe

run_recipe

Run a recipe: a ready-made job of several actions, such as local businesses of one kind in one place with their emails (or only those with weak reviews), new companies with contacts or companies with a reason to call now in any country (contracts, new registrations, funding or hiring, with a signal date, the person to reach and checked emails; Estonia adds year-on-year tax figures), a visibility report for a website (country, language, questions and optional competitors), a company list with industry, size and register entry, checked work emails for a list of people, a brief on a company and a person before a sales call, a pitch or an interview, with optional news and public posts, or companies that just raised money, use a named tool or won a public contract, each with the person to reach and a checked work email, or the social media accounts of one kind of business in one place, with when each started and how many followers it has. Visibility accepts English country/language names or codes. Reason-to-call groups Estonian contract lines by company and defaults to a 1,000 euro company total floor (minimum: 0 disables it). For emails with TikTok, include Instagram; TikTok returns no website. The first choice for a person who is not a developer. Without id: the list of recipes and their inputs. With id and inputs: the price of the whole job and a consent sentence; nothing runs. With max_cost_usd as well (once the person agrees): it runs under that total and answers the rows; a longer run answers a run_id, and run_id reads on. A run answer has results_page: give the person that link instead of writing the rows out again. Only delivered results are charged. NOT for: one action alone, which is run_capability.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "run_recipe"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNoA recipe id from this tool's own list, such as company-list. Left out, the answer is the list.
inputsNoThe recipe's inputs, by name, as its entry in the list names them.
run_idNoWith id: the run_id an earlier call answered, to read that run.
max_cost_usdNoThe most the whole run may cost, in USD, such as "0.50". Left out, the answer is the price and nothing runs.
idempotency_keyNoOptional: your own key for this run, 8 to 64 letters, digits or hyphens. It becomes the run_id.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.7/5.0
Behavior3/5

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

Annotations already flag a non-read-only, open-world, non-idempotent operation, and the description adds genuinely useful context on top: nothing runs without max_cost_usd, 'Only delivered results are charged', the consent sentence, results_page instead of repeating rows, and quirks like TikTok returning no website. However, the recipe-specific caveats (visibility accepting country/language names or codes, the Estonian 1,000 euro floor) read as domain trivia embedded in an enumeration rather than a clean behavioural profile.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single sprawling run-on sentence packs dozens of recipe examples with parenthetical asides before any of the operational rules appear. The critical mode logic and the run_capability exclusion sit at the very end, so the reader must wade through a catalogue to reach what matters.

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 complex, nested-input, costly execution tool with no output schema, it covers the essentials: the three call modes, pricing and consent, how to surface results via results_page, and billing on delivered results only. The main gap is that the nested inputs object is only described by reference to the list entry, leaving the agent dependent on a prior call to know its shape.

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

Parameters3/5

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

Schema coverage is 100%, so the schema already documents all five parameters, giving a baseline of 3. The description does add workflow meaning the schema cannot express — id absent means list, id plus inputs means price only, max_cost_usd plus id means execute, run_id means resume — but these are scattered inside an unstructured sentence rather than tied to the parameter names.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening sentence gives a specific verb and resource ('Run a recipe: a ready-made job of several actions') and the closing line explicitly excludes the single-action case in favour of run_capability, so an agent can place it against siblings. The very long enumeration of example recipes that follows dilutes rather than sharpens that core statement.

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 lays out a complete mode decision tree: no id returns the recipe list, id plus inputs returns price and a consent sentence with nothing running, adding max_cost_usd actually executes, and run_id reads an earlier run on. It also names the alternative for the single-action case ('NOT for: one action alone, which is run_capability').

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.