Skip to main content
Glama
Crawlora-org

Crawlora MCP

Official

opendota_scenarios

Fetch Dota 2 scenario win rates for item timings, lane roles, and misc events like first blood using validated filters before upstream calls.

Instructions

OpenDota Dota 2 scenario win rates. Returns OpenDota's scenario datasets as games, wins and win rate rows, most games first. kind selects item-timings (an item bought by a time for a hero), lane-roles (a hero in a lane role at a time) or misc (courier kill, first blood and chat scenarios by side and region). Filters are validated before any upstream call: hero_id and item apply to item-timings, hero_id and lane_role to lane-roles, scenario to misc.

Input Schema

NameRequiredDescriptionDefault
itemNoItem name from opendota-constants item_ids, for example bfury; item-timings only
kindYesDataset; one of item-timings, lane-roles, misc
limitNoNumber of rows to return, 1 to 2000, most games first; defaults to all
hero_idNoPositive hero ID from opendota-heroes; item-timings and lane-roles only
scenarioNoScenario; one of courier_kill, first_blood, neg_chat_1min, pos_chat_1min; misc only
lane_roleNoLane role 1 to 4 (1 safe lane, 2 mid, 3 off lane, 4 jungle); lane-roles only

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.17.18

TDQS

A3.6/5.0
Behavior3/5

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

With no annotations, the description carries the full burden, and it does disclose useful traits: filters are validated before any upstream call (fail-fast), results are ordered most-games-first, and each row carries games/wins/win rate. However, it does not state read-only semantics, error behavior, or any rate/coverage caveats, leaving real gaps for a data query tool.

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?

Front-loaded with purpose and output shape, then packed with the dataset/filter mapping in one tight block with no filler. It is dense but the density is all substantive, not padding.

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?

For a six-parameter, one-required-argument query tool with no output schema, the description covers the output columns, ordering, dataset semantics, and filter validity, which is close to what an agent needs to call it correctly. Only the read-only/error characteristics remain 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 coverage is 100% and the schema already labels each filter with its applicable `kind` (e.g. 'item-timings only'), so the description's per-kind filter mapping largely repeats structured data. The only added nuance is the pre-flight validation behavior, which is marginal above 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?

States a concrete resource and return shape: "OpenDota's scenario datasets as games, wins and win rate rows, most games first," plus a verb ("Returns"). An agent can distinguish this from sibling aggregation tools like opendota_benchmarks or opendota_hero_stats by the 'scenario win rates' framing, though no sibling is named explicitly.

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?

Explains how to choose among the three datasets via `kind` and which filters are valid for each branch, which is effectively usage guidance for the main decision. It stops short of stating when NOT to use this tool or naming alternative endpoints for related questions.

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