Skip to main content
Glama

Check an API request

check_api_request
Read-onlyIdempotent

Check an HTTP request for a CDP before you send it: is it a call the CDP's own developer docs document for one of five everyday jobs (send an event, create or update a profile, send a batch, look up a profile, delete a person), on a documented host, with the credential in a documented place and every required header, query parameter and body field? Uses the answer keys of CdpHub's agent readiness test, written by hand from each vendor's reference pages, for the 29 CDPs the test scored. It checks the request's form, not your data, and sends nothing to the vendor. Give the request as an object (method, url, headers, query, body) or as a curl command. Leave the job out to find the job it matches.

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": "check_api_request"
  }
}

Input Schema

NameRequiredDescriptionDefault
cdpYesThe CDP, by name or CdpHub slug, for example "Braze", "Segment" or "treasure-ai".
jobNoThe job the request is for. Leave it out to find the job it matches.
curlNoThe request as a curl command, instead of request.
requestNoThe request: method, full url, and headers, query and body as objects. Placeholders in angle brackets are fine.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive/openWorld=false, and the description reinforces rather than contradicts them by stating it 'sends nothing to the vendor' and checks form, not data. It also discloses a real limitation not in the structured fields: coverage is limited to the 29 CDPs the test scored. It stops short of saying what a failure response 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 purpose leads the first sentence and the qualifying details follow in a logical order; the second and third sentences cover provenance and side-effect safety. It is dense but nearly every clause carries information, with the hand-written-answer-keys provenance the closest thing to filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Input handling, scope limits, and side effects are well covered, but there is no output schema and the description never says what the tool returns — pass/fail, a list of violations, or a matched job when 'job' is omitted. For a validation tool whose whole value is the verdict, that is a meaningful gap.

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 100%, so the baseline is 3, but the description adds meaning by translating the job enum into plain language (send an event, create or update a profile, send a batch, look up a profile, delete a person) and by restating the two alternative input forms (object vs curl). It does not clarify any mutual-exclusivity or precedence rules beyond what the schema says.

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 names a specific verb and resource ('check an HTTP request for a CDP') and then enumerates exactly what is validated: documented job, documented host, credential placement, required headers/query/body. It also bounds the scope to the 29 CDPs scored by CdpHub's agent readiness test, which makes it unmistakable against siblings like get_cdp or compare_cdps.

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

Usage Guidelines4/5

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

It gives clear timing guidance ('before you send it') and an explicit optional-parameter rule ('Leave the job out to find the job it matches'). What it lacks is an explicit alternative or exclusion — e.g. it never says to use get_api_recipe when you want to construct a request rather than validate one.

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