Skip to main content
Glama

import_demo

Analyzes an existing CS2 demo file stored in a configured server import folder and returns match and job IDs for tracking analysis progress and retrieving results.

Instructions

Analyze a demo file that already exists on the server's disk (inside one of the configured import folders). To upload from elsewhere use the REST API: POST /api/v1/matches (multipart field file). Returns match_id and job_id; wait with get_job, then call get_match.

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": {
      "path": "<path>"
    },
    "name": "import_demo"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathYesAbsolute path to a .dem (or .dem.gz/.bz2/.zip) file.
auto_render_topNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations only say readOnlyHint=false, destructiveHint=false, openWorldHint=false, so the description must add the behavioral shape — and it does, disclosing that this is an asynchronous job (returns match_id and job_id, wait with get_job) and that it only reads from configured import folders, which bounds its side effects. It stops short of saying what happens on an invalid/out-of-folder path or how long analysis takes.

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 sentences, front-loaded with the scope constraint, then the fallback path, then the async follow-up workflow. No filler and nothing repeated from the schema.

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 an async mutation-style tool, the description covers the input constraint, the returned identifiers, and the polling workflow, which is what an agent needs to sequence calls; an output schema exists so return values needn't be spelled out. The remaining gap is the undocumented `auto_render_top` parameter, which an agent cannot reason about.

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 coverage is 50%: `path` is well described in the schema, and the description usefully adds the constraint that the path must resolve inside a configured import folder. However, `auto_render_top` (0-20 integer, default null) is never mentioned in the schema description or the prose, so its meaning — presumably how many top clips to auto-render — is left to inference.

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 (analyze) and resource (demo file), plus the crucial scope constraint that the file must already exist on the server's disk inside a configured import folder. That constraint alone separates it from an upload/import path, and the agent can tell what the tool does without opening the schema.

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 an explicit when-to-use condition (file already on server disk) and an explicit alternative for the other case (REST API POST /api/v1/matches with multipart field `file`). It also lays out the follow-up sequence: wait with get_job, then call get_match. The only gap is that it points to a raw REST endpoint rather than naming the sibling import_matches tool, which an agent inside this MCP surface may prefer.

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