Skip to main content
Glama
hkaanengin

opendota-mcp-server

by hkaanengin

get_benchmarks

Retrieve percentile-based benchmark stats for any Dota 2 hero to compare player performance against average, good, and exceptional thresholds across key metrics like GPM, XPM, and KDA.

Instructions

Get statistical benchmarks for a hero (average performance metrics across all skill levels).

Use this when users ask:

  • "What are the average stats for [hero]?"

  • "What's a good GPM/XPM for [hero]?"

  • "Show me benchmark stats for [hero]"

  • "What's the typical performance for [hero]?"

  • "How do I compare to other [hero] players?"

Returns percentile-based benchmarks showing what constitutes below-average, average, good, and exceptional performance for various metrics on this hero. Useful for comparing a player's performance to the general population.

Supports both hero IDs and natural language hero names.

Args: hero_id: Hero to get benchmarks for. Accepts: - Integer: Hero ID (e.g., 86 for Rubick) - String: Hero name (e.g., "Rubick", "Anti-Mage")

Returns: Dictionary containing benchmark statistics organized by metric. Each metric shows percentile breakdowns (e.g., 0.1, 0.25, 0.5, 0.75, 0.9) representing the 10th, 25th, 50th (median), 75th, and 90th percentiles.

Common metrics included:
- gold_per_min: GPM benchmarks by percentile
- xp_per_min: XPM benchmarks by percentile
- kills_per_min, deaths_per_min, assists_per_min: KDA-related benchmarks
- last_hits_per_min: Farming efficiency benchmarks
- hero_damage_per_min: Combat effectiveness benchmarks
- hero_healing_per_min: Support/healing benchmarks
- tower_damage: Objective damage benchmarks
- stuns_per_min: Crowd control benchmarks
- And many more...

Common queries: - General benchmarks: get_benchmarks("Rubick") - Compare player stats: First get player stats with get_player_totals(), then compare to benchmarks from this function

Example: get_benchmarks("Rubick") -> { "gold_per_min": { "0.1": 250.5, # 10th percentile - below average "0.25": 310.2, # 25th percentile - low average "0.5": 380.7, # 50th percentile (median) - average "0.75": 450.3, # 75th percentile - above average "0.9": 520.8 # 90th percentile - excellent }, "kills_per_min": { "0.1": 0.15, "0.5": 0.35, "0.9": 0.65 }, ... }

Interpretation: If a player has 460 GPM on Rubick, they're performing around the 75th percentile (better than 75% of Rubick players).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
hero_idYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Behavior5/5

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

With no annotations, the description carries the full burden of behavioral disclosure. It explains the return is percentile-based, shows a detailed example output with percentiles, and describes how to interpret results (e.g., 'If a player has 460 GPM on Rubick, they're performing around the 75th percentile'). This is exemplary transparency.

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?

The description is well-structured with clear sections and front-loaded purpose, but it is somewhat lengthy. There is minor redundancy between the initial bullet list of queries and the later 'Common queries' section. Still, every section contributes useful information, and the example output earns its place.

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?

For a one-parameter tool with no annotations, the description is remarkably complete. It covers input formats, output structure, common metrics, example usage, and interpretation. Even though an output schema exists, the description's Returns section adds clarity about percentile semantics and metric names.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema only defines hero_id as integer or string with zero description. The tool description compensates fully by stating it accepts hero IDs (e.g., 86) or hero names (e.g., 'Rubick', 'Anti-Mage'), giving examples and clarifying the flexible input format. This adds substantial meaning beyond the raw schema.

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?

The description opens with a specific verb+resource: 'Get statistical benchmarks for a hero' and clarifies it provides 'average performance metrics across all skill levels.' This clearly distinguishes it from sibling tools like get_player_histograms or get_player_totals by focusing on percentile-based benchmarks for a single hero.

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?

Explicitly lists example user queries (e.g., 'What are the average stats for [hero]?') and even recommends a workflow: 'First get player stats with get_player_totals(), then compare to benchmarks from this function.' This names an alternative tool and provides sequencing, exceeding the basic 'when to use' requirement.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/hkaanengin/opendota-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server