Skip to main content
Glama

Batru — Dota 2, Deadlock & Marvel Rivals win predictor

by gg.batru

get_model_track_record

Read-only

Get batru.gg's public model evaluation ledger — every weekly test, wins AND losses.

batru.gg publishes EVERY champion-vs-challenger evaluation of its Dota 2
model (promoted or rejected), auto-generated from the promotion gate's
append-only log — nothing is hand-picked. Use this when a user asks whether
the model is any good or how it is validated.

HOW TO PRESENT IT: lead with CALIBRATION (ECE — lower is better; ~0.006
means a stated 60% wins ~60% of the time), then BCE. Do NOT headline raw
accuracy: Dota drafts are balanced by design, so ~55% is near the
game-imposed ceiling for ANY model — calibration is the meaningful claim.

Args:
    limit: Max evaluations to return, newest first (default 10).

Returns {generated_at, ledger, total_evaluations, total_promotions,
evaluations:[{decided_at, promote, challenger:{ece,bce,acc},
champion:{ece,bce,acc}, holdout_n}]}. Report numbers verbatim.

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

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNo
contextYesExplain 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."

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds valuable context: the ledger is auto-generated from an append-only log, nothing is hand-picked, and it includes both promoted and rejected evaluations. This clarifies the data's provenance and neutrality, going beyond the annotation's safety profile.

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 moderately detailed but well-structured: it states purpose first, then usage context, presentation guidance, parameters, and return format. While longer than typical, each section serves a purpose (especially the nuanced 'how to present it' guidance), so it earns its length.

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 covers purpose, when to use, how to present results, the 'limit' parameter, and the complete return shape (including nested fields). There is no output schema, so this description carries the full burden, and it does so comprehensively enough for an agent to invoke and interpret results correctly.

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 description coverage is 50%, with only 'context' described in the schema. However, the description supplements by explaining 'limit' (Max evaluations to return, newest first, default 10) and also details the return structure, which helps interpret parameter effects. This adds meaningful semantic value beyond the schema alone.

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 retrieves batru.gg's public model evaluation ledger, listing every weekly test with wins and losses. It uses a specific verb ('Get') and resource, and it is distinct from sibling tools that focus on game meta stats (Dota, Deadlock, Marvel Rivals).

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 says 'Use this when a user asks whether the model is any good or how it is validated.' It also provides presentation instructions, clarifying what to emphasize (calibration over raw accuracy) and when not to headline accuracy, which serves as guidance for appropriate use.

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

All Batru — Dota 2, Deadlock & Marvel Rivals win predictor toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.6/5.0
Disambiguation4/5

Most tools are clearly separated by game prefix and metric family (tier list, counters, matchup, synergy, momentum, ban rates), so an agent can generally pick the right one. A few close pairs—counters vs. matchup and recommend vs. predict/batch—have adjacent purposes, and get_more_tools is a vague catch-all, so it is not quite a perfect 5.

Naming Consistency4/5

With a few exceptions the set follows a consistent get_<game>_<metric> / predict_* / recommend_* snake_case pattern. Deviations such as predict_dota_winrate instead of predict_dota_draft, predict_dota_winrate_batch, lookup_hero, and get_more_tools break the otherwise tidy pattern.

Tool Count2/5

32 tools is above the 25+ threshold and makes the server heavy even though the tri-game structure is logical. Many parallel families could be parameterized by game, and get_more_tools adds count without a clear domain purpose.

Completeness4/5

The read-only analytics surface is broadly complete: every game has tier lists, counters, matchups, synergies, momentum, draft prediction, and pick recommendations, plus Dota tournament coverage and a model track record. Gaps are minor—Dota lacks ladder ban rates, Deadlock and Marvel Rivals lack tournament stats and model evaluation ledgers, and their draft advice is only heuristic until six heroes are provided.

Resources