Skip to main content
Glama

Prepare project download

get_project_file

Get a requested result by workspace-relative path, latest scene/render/video/model, or output_id returned by an explicit external-path file tool. Local: disk path. Remote: a temporary download link. External output permissions last 24 hours in the current Desktop/MCP processes and cannot read other external files.

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": "get_project_file"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathNoWorkspace-relative result path returned by list_project_files; not an arbitrary file on the chat device.
latestNoRetrieve the latest completed result of this category instead of naming a path.
output_idNoIdentifier returned by an explicit external-path output operation in this Desktop/MCP lifetime.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedInput schema / properties / latest / description
      Added value: +"Retrieve the latest completed result of this category instead of naming a path."
    • addedInput schema / properties / output_id / description
      Added value: +"Identifier returned by an explicit external-path output operation in this Desktop/MCP lifetime."
    • addedInput schema / properties / path / description
      Added value: +"Workspace-relative result path returned by list_project_files; not an arbitrary file on the chat device."
  2. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Annotations only say readOnlyHint=false and idempotentHint=false without explaining why; the description fills that gap by disclosing that remote access produces a temporary download link and that external-output permissions expire after 24 hours per Desktop/MCP lifetime. That is meaningful side-effect and authorization context the annotations do not carry. It does not cover failure behavior for expired or unknown output_ids.

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?

Three short sentences, front-loaded with the core action and then the local-vs-remote delivery distinction. The telegraphic 'Local: disk path. Remote: a temporary download link.' style is efficient, though slightly compressed to the point of needing parsing.

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?

All three parameters are optional and there is no output schema, so the description bears the burden of explaining the return shape and it only partly does (disk path vs. temporary link). It never states precedence when path, latest, and output_id are combined, nor what is returned when no argument is given.

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 100%, so each parameter is already documented. The description reinforces the path and latest semantics and adds the 24-hour lifetime qualifier for external output_ids, but adds little beyond what the schema says about enumerations or mutual exclusivity of the three optional inputs.

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?

States a specific verb and resource ('Get a requested result') and immediately enumerates the three accepted addressing modes: workspace-relative path, latest category, or output_id. The phrase 'output_id returned by an explicit external-path file tool' implicitly separates it from other file-viewing siblings, though no sibling is named outright.

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?

Gives clear selection context for each input mode and an explicit scope boundary ('cannot read other external files', 'not an arbitrary file on the chat device' per schema). It stops short of naming list_project_files or view_download as the alternative path, and does not say what happens if several addressing parameters are supplied at once.

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