OneSimpleAPI

GET|HEAD /api/files

api_get_files

Destructive

Existing api/files API operation. Uses the OneSimpleAPI API (https://onesimpleapi.com/docs), with the same permissions, credits and storage. Supply API parameters in query or body. method defaults to GET. Outputs preserve HTTP status, headers and JSON/text/base64 body; redirects are returned without following them.

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_get_files"
  }
}

Input Schema

Name	Required	Description
`body`	No	API request body. Nested objects, arrays, HTML, base64 data and all API options retain their original meaning.
`path`	No
`files`	No	Multipart uploads keyed by API field name (for example pdf). Supply file_name, base64 bytes and optional mime_type. Uploads use the existing API file validators.
`query`	No	URL query parameters. Sensitive API options must be in body as documented by the API.
`method`	No
`headers`	No	API request headers such as Idempotency-Key, Range and If-None-Match. Authentication and transport headers are managed by the connection.
`content_type`	No	Defaults to application/json, or multipart/form-data when files are supplied.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 5, 2026

TDQS

C2.8/5.0

Behavior3/5

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

Annotations already declare openWorld, destructive and non-idempotent behavior, so the bar is lower, and the description adds genuinely useful context: same permissions/credits/storage as the rest of the API, method defaults to GET, and redirects are returned unfollowed. It does not reconcile the disconnect between a GET/HEAD call and the destructiveHint=true annotation, nor explain that the url/status body parameters route to delete/list handlers.

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

Conciseness3/5

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

One dense paragraph, front-loaded with a tautological opener ("Existing api/files API operation") and low-value boilerplate about credits and storage. The concrete behavioral facts (redirect handling, output preservation) are buried at the end rather than leading.

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?

For a 7-parameter, nested-object, no-output-schema proxy tool, the description covers transport behavior but leaves the agent guessing what the operation actually does at the domain level (what is listed, what the url/status parameters mean, why a GET is flagged destructive). It is adequate but leaves real gaps for a tool carrying a destructive annotation.

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 description coverage is 71%, so the schema carries most parameter meaning (files upload shape, content_type default, header examples). The description only adds the generic rule that parameters go in query or body and that sensitive options belong in the body, without clarifying the purpose of url/status or when to use headers.

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

Purpose3/5

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

The description says it is an "Existing api/files API operation" on the OneSimpleAPI service with a default GET method, so the resource and verb are inferable. However, the opening sentence essentially restates the tool name/title, and it never distinguishes this call from siblings like api_delete_files or api_post_files_capture_link that touch the same files resource.

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

Usage Guidelines2/5

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

There is no statement of when to use this tool versus alternatives, nor when to pick HEAD over GET. The only operational hint is mechanical ("Supply API parameters in query or body"), which is invocation mechanics rather than usage guidance.

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

All OneSimpleAPI tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?