Skip to main content
Glama
WebCake Storefront MCP

WebCake Storefront MCP

by vuluu2k

api_call

Executes cataloged storefront API operations by ID or method and path, checks required keys, and dry-runs writes so you can preview requests before sending.

Instructions

Run any operation from api_find by id (GET, POST, PUT, PATCH, DELETE). Writes default to dry_run:true and return exactly what would be sent — show the user, then repeat with dry_run:false. Refuses writes to routes a dedicated tool owns (it names the tool) and irreversible account operations. Required keys are checked against the call sheet before sending.

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": "api_call"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNoOperation id from api_find (preferred)
bodyNoJSON body for POST/PUT/PATCH/DELETE (keys from the call sheet)
pathNoCatalog path with :params, e.g. /api/v1/dashboard/site/:site_id/product_tags/all
pickNoKeep only these fields on each item of a list result (or on a single object)
queryNoQuery-string values
methodNoWith path, when id is not given
dry_runNoDefault true for writes: describe, don't send
max_itemsNoCap list results (default 50)
path_paramsNoValues for :params in the path; site_id defaults to the current site

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv2.8.0

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only declare readOnlyHint:false; the description carries the real behavioral load. It discloses that writes default to a dry run returning exactly what would be sent, that certain routes are refused with the owning tool named, and that required keys are validated against the call sheet before sending — meaningful pre-flight and safety context beyond the annotation.

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

Conciseness5/5

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

Three front-loaded sentences with no filler: capability, write-safety workflow, and refusal/validation rules in that order. Every sentence adds a distinct operational fact.

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 9-parameter, nested-body arbitrary-call tool with no output schema, the description covers invocation, safety, and refusal behavior well. It is thinner on what a real (non-dry-run) response looks like or how failures surface, but the dry-run promise of 'exactly what would be sent' partially compensates.

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 description coverage is 100%, so the parameters are already documented; the description mainly reinforces the dry_run default and the id-from-api_find source. It adds genuine workflow meaning by explaining why dry_run exists (show then repeat) rather than just restating the field.

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+resource: it executes any operation catalogued by api_find, by id, across all HTTP methods. The tie to api_find makes it immediately distinguishable from siblings like api_get or api_find without opening a 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 workflow: find the id with api_find, run with the default dry_run:true, show the user, then repeat with dry_run:false. It also names when NOT to use it — routes owned by a dedicated tool (which it names) and irreversible account operations — so the agent has both routing and exclusion guidance.

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