Batru — Competitive Game Intelligence for AI Agents

recommend_pick

Read-only

Best heroes to pick next against this draft — Dota 2, Deadlock or Marvel Rivals.

Per-game semantics:
- dota2: top 3 picks scored by the CALIBRATED draft model (each with the
  calibrated team win rate after adding that hero); `my_side` applies.
- deadlock / marvel-rivals: ranked by REAL observed pair data (win rate
  vs the enemy heroes, blended with duo rate alongside your picks) — an
  empirical heuristic, not the calibrated model; verify a full 6v6 with
  predict_winrate.

Args:
    game: "dota2", "deadlock", or "marvel-rivals".
    enemy_heroes: Enemy heroes to pick against.
    my_heroes: Heroes your team already has.
    my_side: Dota only — "radiant" (default) or "dire".
    limit: Max recommendations (Deadlock/Marvel; Dota returns top 3).

Report win rates verbatim.

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.
`limit`	No	Max recommendations (Deadlock / Marvel Rivals; Dota always returns its top 3).
`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`	No	Heroes your team already has, as a list of hero names (may be empty).
`enemy_heroes`	Yes	Enemy heroes to pick against, as a list of hero names.

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedSep 19, 2026

addedInput schema / properties / enemy_heroes / description

Added value: +"Enemy heroes to pick against, as a list of hero names."

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 / limit / description

Added value: +"Max recommendations (Deadlock / Marvel Rivals; Dota always returns its top 3)."

addedInput schema / properties / my_heroes / description

Added value: +"Heroes your team already has, as a list of hero names (may be empty)."

addedInput schema / properties / my_side / description

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

addedInput schema / properties / my_side / enum
```
Added value: +[
+  "radiant",
+  "dire"
+]
```

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.\""

AddedSep 12, 2026

TDQS

A4.5/5.0

Behavior4/5

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

The tool has annotations readOnlyHint=true, destructiveHint=false, and openWorldHint=true. The description adds behavioral context by explaining the difference between the calibrated model for Dota and the empirical heuristic for other games, and instructs to report win rates verbatim and show citations. This goes beyond the annotations, which only indicate read-only and open-world hints.

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 per-game semantics and a parameter list, but it is somewhat verbose with the long context parameter description and the instruction to report win rates. The core purpose is front-loaded, but the parameter list could be more concise by removing redundant information already in the schema.

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?

The description is complete for a tool with no output schema, as it explains the return values (top 3 for Dota, limit for others, win rates to report) and how to present citations. It also covers cross-game differences and gives a clear call-to-action for verification with predict_winrate, making it fully adequate for an agent to call correctly.

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?

Schema coverage is 100% as every parameter has a description. The description adds value by explaining the meaning of my_side (only for Dota), the limit's behavior (only for Deadlock/Marvel, Dota always returns top 3), and the context parameter's analytics purpose. It clarifies that my_heroes may be empty and reinforces the required nature of game and enemy_heroes, going beyond the schema's basic text.

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 clearly states the tool's purpose: recommending the best heroes to pick next against an enemy draft, and explicitly lists the supported games. It distinguishes itself from sibling tools by noting that for Deadlock/Marvel Rivals it uses real observed pair data and recommends verifying with predict_winrate, which helps differentiate it from other draft-analysis tools like analyze_draft or get_counters.

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 provides clear per-game semantics, explaining that Dota uses a calibrated model while other games use an empirical heuristic, and even suggests verifying full 6v6 with predict_winrate. However, it does not explicitly state when not to use this tool or mention alternatives beyond predict_winrate, but the context is sufficient for most use cases.

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.

recommend_pick

Input Schema

Schema Changelog

TDQS

Glama MCP Gateway

Resources