Skip to main content
Glama
Crawlora-org

Crawlora MCP

Official

opendota_hero_stats

Retrieve and filter Dota 2 hero stats, including base stats and pick/win/ban counts with win rates for pro, public, turbo, and rank brackets; sort by attribute, attack type, or role.

Instructions

OpenDota Dota 2 hero pick and win statistics. Returns every Dota 2 hero with base stats (health, mana, armor, attack range, move speed) and OpenDota's aggregate pick/win counts and win rates for professional games (with bans), public games, turbo, and each of the eight rank brackets (Herald, Guardian, Crusader, Archon, Legend, Ancient, Divine, Immortal). Filter by primary_attr (agi, all, int, str), attack_type (Melee, Ranged) and role, sort with sort and desc, and cap with limit. Win rates are percentages and are omitted when there are no picks.

Input Schema

NameRequiredDescriptionDefault
descNoSort descending (the default for every key except id and name)
roleNoRole filter; one of Carry, Disabler, Durable, Escape, Initiator, Nuker, Pusher, Support
sortNoSort key; one of id, name, pro_pick, pro_win, pro_ban, pro_win_rate, pub_pick, pub_win, pub_win_rate, turbo_pick, turbo_win_rate; defaults to id
limitNoNumber of heroes to return, 1 to 200; defaults to all
attack_typeNoAttack type filter; one of Melee, Ranged
primary_attrNoPrimary attribute filter; one of agi, all, int, str

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.17.18

TDQS

A3.7/5.0
Behavior4/5

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

With no annotations present, the description carries the full burden and does disclose meaningful behavior: the exact response surface (base stats plus per-bracket pick/win counts), the presence of pro bans, that win rates are percentages, and that they are omitted when there are no picks. It does not mention pagination beyond limit or any rate/auth constraints, which is the only real gap.

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 core payload and the bracket enumeration are front-loaded, and every clause is informational rather than filler. It is a single dense paragraph, but the length is justified by the breadth of returned data and the filter set.

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?

There is no output schema, so the description must describe return values and does: hero base stats plus pick/win/win-rate figures across pro, public, turbo, and rank brackets, with a note on omitted win rates. It is complete enough to call correctly; only field naming and pagination behavior are left unstated.

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 the enum values, defaults, and the desc semantics are already fully documented. The description largely restates those filters and only adds the framing that sort and desc pair together and that limit caps the result set, which is marginal beyond the schema baseline.

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 states a concrete verb and resource: it returns every Dota 2 hero with base stats plus OpenDota aggregate pick/win counts broken out by pro, public, turbo, and eight rank brackets. That scope is specific enough to separate it from siblings like opendota_heroes or opendota_hero_matchups, although it never names an alternative directly.

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?

Use is strongly implied by the enumerated dataset (pick/win rates across brackets), so an agent can infer this is the stats-lookup tool rather than the roster tool. However, there is no explicit 'use this when… instead of opendota_heroes/opendota_benchmarks' routing, so the guidance stays implicit.

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

Deploy Server

Other Tools