Skip to main content
Glama

Get an API recipe

get_api_recipe
Read-onlyIdempotent

The exact HTTP request a CDP's own developer docs give for an everyday job: send an event (send_event), create or update a profile (upsert_profile), send a batch of events (send_batch), look up a profile (read_profile) or delete a person (delete_user). Each request is written with one shared example (customer u_1001, ada@example.com, order ord_5001) and checked with the rules of CdpHub's agent readiness test; none was sent to the vendor's API. Where the CDP doesn't offer the job, or its docs couldn't be read, the answer says why. Covers the 30 CDPs in the agent readiness test and names the others. Placeholders in angle brackets are for the caller to fill in.

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": {
      "cdp": "<cdp>"
    },
    "name": "get_api_recipe"
  }
}

Input Schema

NameRequiredDescriptionDefault
cdpYesThe CDP, by name or by its CdpHub slug, for example "Braze", "Segment" or "treasure-ai".
jobNoThe job. Leave it out to get all five.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.1/5.0
Behavior5/5

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

Beyond the annotations (readOnly, idempotent, non-destructive, closed-world), the description discloses the critical caveat that 'none was sent to the vendor's API', i.e., the recipes are doc-derived and unverified against live endpoints. It also explains the shared example data used and that angle-bracket placeholders are for the caller to fill in — context no annotation or schema field conveys.

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 in the first clause, followed by the verification caveat and coverage limits; every sentence carries information. It is dense but not padded, though the parenthetical example data could be trimmed.

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?

With no output schema, the description appropriately characterizes the return value (an HTTP request with fill-in placeholders, phrased around a concrete customer/order example) and explains the failure case. It falls short of stating the response format or whether headers/auth details are included, but is otherwise sufficient for a two-parameter read tool.

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% and both parameters are fully documented, including the job enum and the cdp name-or-slug acceptance, so the baseline is 3. The description restates the same five job values in plain language, adding only marginal meaning beyond what the structured enum already provides.

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 description uses a concrete verb-and-resource framing ('The exact HTTP request a CDP's own developer docs give') and enumerates the five supported jobs, so an agent knows precisely what comes back versus a general CDP metadata tool like get_cdp.

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?

It sets clear scope boundaries ('Covers the 30 CDPs in the agent readiness test and names the others', and 'Where the CDP doesn't offer the job... the answer says why'), which tells the agent when the tool will be useful. However, it never explicitly contrasts itself with siblings such as get_cdp, check_stack, or compare_cdps, so the alternative selection is left to inference.

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