Skip to main content
Glama
mcp-feature-test

mcp-feature-test

by linuxrrze

Return files in a tool result

return_files
Read-only

Returns files as embedded text, blob, resource_link, image and audio blocks in one result to reveal which file-handling features a client accepts or drops.

Instructions

Return one tool result containing every way MCP can hand a file to a client: an embedded text resource (CSV), embedded blob resources (PNG and PDF), a resource_link (fetched via resources/read), an image block and an audio block (WAV). The first text block lists them, so you can see which ones the client dropped.

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": "return_files"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.0

TDQS

A3.9/5.0
Behavior4/5

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

Annotations only declare readOnlyHint=true, so the description carries most of the behavioral weight, and it delivers: it discloses that the resource_link must be fetched separately via resources/read and that clients may drop some blocks, with the first text block serving as an inventory. What's missing is any note on size/limits or what a dropped-block report looks like precisely, but the key non-obvious behavior is surfaced.

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?

Two sentences, the second of which adds genuinely new information (the inventory text block). The first sentence is dense with parentheticals listing media types, which slightly slows scanning, but every element enumerated is distinct and purposeful rather than filler.

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

Completeness5/5

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

With no output schema, the description must itself describe the return value, and it does so completely by listing every content block type and the resources/read requirement for the link. For a zero-parameter, read-only probe tool, nothing an agent needs in order to call it or interpret its result is missing.

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?

The schema has zero parameters, so there is nothing for the description to disambiguate and the baseline of 4 applies. The description correctly spends none of its words on parameters and instead explains the return payload.

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

Purpose4/5

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

The description uses a specific verb and resource ("Return one tool result") and then enumerates exactly what that result contains: CSV text resource, PNG/PDF blob resources, a resource_link, an image block, and a WAV audio block. That is far more precise than the title, though it never names or contrasts any sibling tool, so an agent must infer that this is the file-return probe rather than, say, upload_file_experimental.

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?

Usage is only implied: the closing clause about seeing "which ones the client dropped" signals a diagnostic/testing intent, but there is no explicit when-to-use or when-not-to-use statement and no named alternative. An agent can guess this is the tool for exercising file-handoff paths, but the guidance is inferred rather than stated.

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