Batru — Competitive Game Intelligence for AI Agents

Analyze a game draft visually

analyze_draft

Read-only

Analyze a draft and render an interactive Batru win-rate board.

Use this for visual draft, matchup, win-probability, or next-pick questions
in Dota 2, Deadlock, or Marvel Rivals. It combines the existing prediction
and recommendation tools into one stable structured result. Clients that
support MCP Apps render a compact card; every other MCP client receives the
same data as JSON/text. This tool is read-only.

Dota 2 supports partial drafts and returns a calibrated probability plus
calibrated next-pick win rates. Deadlock and Marvel Rivals only return a
calibrated probability for a complete 6v6; partial drafts still return
counter-pick recommendations labelled as empirical pair-data scores.

Args:
    game: "dota2", "deadlock", or "marvel-rivals".
    my_heroes: Your team / Team 0 heroes (0-5 for Dota, 0-6 otherwise).
    enemy_heroes: Enemy team / Team 1 heroes (0-5 for Dota, 0-6 otherwise).
    my_side: Dota only — whether your team is Radiant or Dire.

Returns the two rosters, prediction status, calibrated win rates when
available, recommendations, metric labels, `source_url`, and `citation`.

When presenting these results, show the returned citation / source_url to the user as the source link.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`game`	Yes	Which game: "dota2", "deadlock" or "marvel-rivals". Required — hero names alone do not identify the game.
`context`	Yes	Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution."
`my_side`	No	Dota 2 only: the side your team plays, "radiant" or "dire". Ignored for deadlock / marvel-rivals.	radiant
`my_heroes`	Yes	Heroes already on YOUR team, as a list of hero names (any alias or short name; normalised internally). May be empty for a fresh draft. To see every valid hero name for a game, call lookup_hero with an EMPTY query (query="", game=...) — it returns the full roster (displayName + shortName + aliases).
`enemy_heroes`	Yes	Heroes on the ENEMY team, as a list of hero names (any alias or short name; normalised internally). To see every valid hero name for a game, call lookup_hero with an EMPTY query (query="", game=...) — it returns the full roster (displayName + shortName + aliases).

Output Schema

TableJSON Schema

Name	Required	Description	Default
`game`	Yes
`note`	Yes
`error`	No
`citation`	No
`my_label`	Yes
`my_heroes`	No
`game_label`	Yes
`source_url`	No
`enemy_label`	Yes
`did_you_mean`	No
`enemy_heroes`	No
`my_win_rate_pct`	No
`recommendations`	No
`prediction_status`	Yes
`enemy_win_rate_pct`	No
`recommendation_metric_label`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedSep 19, 2026

addedInput schema / properties / enemy_heroes / description

Added value: +"Heroes on the ENEMY team, as a list of hero names (any alias or short name; normalised internally). To see every valid hero name for a game, call lookup_hero with an EMPTY query (query=\"\", game=...) — it returns the full roster (displayName + shortName + aliases)."

addedInput schema / properties / game / description

Added value: +"Which game: \"dota2\", \"deadlock\" or \"marvel-rivals\". Required — hero names alone do not identify the game."

addedInput schema / properties / my_heroes / description

Added value: +"Heroes already on YOUR team, as a list of hero names (any alias or short name; normalised internally). May be empty for a fresh draft. To see every valid hero name for a game, call lookup_hero with an EMPTY query (query=\"\", game=...) — it returns the full roster (displayName + shortName + aliases)."

addedInput schema / properties / my_side / description

Added value: +"Dota 2 only: the side your team plays, \"radiant\" or \"dire\". Ignored for deadlock / marvel-rivals."

Changed1 schema field changedSep 12, 2026

changedInput schema / properties / context / description

Previous value: -"Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include sensitive information such as credentials, passwords, or personal data. Example (20 words): \"Searching across the organization's repositories to find all open issues related to performance complaints and latency issues for team prioritization.\""New value: +"Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as \"a user\", \"the customer\", or \"an account\". Example: \"Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution.\""

AddedAug 28, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Annotations already mark readOnlyHint=true, and the description reinforces that the tool is read-only. It adds meaningful behavioral detail beyond annotations: MCP Apps render a compact card while other clients get JSON/text, Dota 2 supports partial drafts with calibrated probability and next-pick win rates, and Deadlock/Marvel Rivals only return calibrated probability for complete 6v6 drafts. This is exactly the kind of context that helps an agent understand side effects and output variability.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The main behavior is front-loaded and well written, but the Args block repeats much of the schema's parameter documentation and includes a long privacy instruction already present in the schema. The sentence about presenting citation/source_url also feels misplaced. The description is adequate but not as tight as it could be.

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 tool with this complexity, the description is thorough: it covers supported games, partial-draft behavior per game, output rendering differences, read-only semantics, and a presentation note for citations. Since an output schema exists, the description does not need to enumerate return fields in detail.

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?

Schema coverage is 100%, so the schema already documents every parameter. The description adds useful semantics beyond the schema, especially the count constraints: my_heroes is 0-5 for Dota 2 and 0-6 otherwise. Most other Args text duplicates schema descriptions, but this added constraint is valuable for avoiding invalid calls.

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 and resource: analyze a draft and render an interactive Batru win-rate board. It explicitly names the supported games and says it combines prediction and recommendation, which clearly distinguishes it from sibling tools like predict_winrate, recommend_pick, and get_matchup.

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?

The description states when to use the tool: for visual draft, matchup, win-probability, or next-pick questions. It also explains that it combines existing prediction and recommendation tools. It does not explicitly list exclusion cases for individual sibling tools, but the guidance is strong enough for an agent to select it appropriately.

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

All Batru — Competitive Game Intelligence for AI Agents tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.