Skip to main content
Glama

Call a deployed endpoint for real

call_endpoint
Destructive

Sends a real HTTP request to a deployed endpoint and reports status, content type, and body to verify the live URL, path, method, and API key work.

Instructions

Makes a REAL HTTP request to a deployed endpoint — the same request a browser or a customer makes — and reports the status, content type and body. This is the ONLY check that goes through the live URL: the deployment, the path, the allowed verbs and the API key are all exercised, and none of them are visible to test_block or execute_workspace, which talk to the sandbox directly. Run it as the last step of anything with a URL in it, and FIRST when a page's own calls are failing: a 404 here means nothing is deployed at that path (setting endpointPath on a block publishes nothing — deploy_endpoint does), while a 500 means the block behind it threw. Name the domain and the path; the URL is built from that domain's own baseUrl, so there is no address to pass and no way to test a URL that is not the one your users were given. The request really runs the block and counts as one API call.

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": {
      "domainId": "<domainId>",
      "path": "<path>"
    },
    "name": "call_endpoint"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyNoRaw body, as a string. Sent as application/json unless you set a Content-Type header.
pathYesThe deployed path, e.g. "api/orders". Empty string is the domain root.
queryNo
apiKeyNoOnly for an endpoint deployed with isAnonymous:false — mint one with create_domain_api_key. Sent as a bearer token.
methodNoGET (default), POST, PUT, PATCH, DELETE or HEAD.
headersNo
domainIdYesThe domain's id — from list_domains.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.53.0

TDQS

A4.7/5.0
Behavior5/5

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

Annotations only say destructiveHint=true; the description explains why it bites — the request 'really runs the block and counts as one API call' — and decodes outcomes (404 = nothing deployed at that path, 500 = the block threw). It also discloses the API-key/auth path and that arbitrary URLs cannot be tested because the URL is derived from the domain's baseUrl.

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?

Densely front-loaded: purpose first, then exclusivity, then usage ordering, then mechanics and cost. Every clause carries information, though the single unbroken paragraph is heavy and the parenthetical about endpointPath vs deploy_endpoint slightly interrupts the flow.

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 7-parameter, no-output-schema, side-effecting tool the definition covers what matters: live-vs-sandbox distinction, URL construction, auth, error interpretation, and billing side effect. It does not describe the response beyond 'status, content type and body', but that is sufficient given there is no output schema to reconcile.

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 71%, and the description adds real meaning the schema cannot: domainId plus path are composed into a URL from that domain's baseUrl, so there is 'no address to pass,' and path semantics ('Empty string is the domain root' lives in the schema, but the composition rule does not). It leaves query/headers unexplained, which is acceptable given the per-param schema text.

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 and resource — a REAL HTTP request to a deployed endpoint — and immediately delimits it from sandbox tools: test_block and execute_workspace 'talk to the sandbox directly.' The agent can pick this tool over its siblings without opening any 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 explicit ordering rules ('run it as the last step of anything with a URL in it' and 'FIRST when a page's own calls are failing') plus the deployment prerequisite (deploy_endpoint must have run; setting endpointPath publishes nothing). Alternatives are named by function, not just by name.

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