player_heroesFetch the top heroes played by a Dota 2 player (by Steam account id), ranked by match count — returns heroId, matchCount, and winCount for up to take heroes (default 20).
| Name | Required | Description | Default |
|---|---|---|---|
| take | No | ||
| _apiKey | Yes | Your own STRATZ API token (BYO — Pipeworx does not supply one). Free at https://stratz.com/api after Steam sign-in. | |
| steam_account_id | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish readOnly/openWorld/idempotent and non-destructive. The description adds useful behavioral detail not in annotations: ordering by match count, returned fields (heroId, matchCount, winCount), and default/limit behavior of take. No contradiction.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
One sentence that front-loads the verb, resource, and ranking criteria, then adds return fields and default in a compact clause. No filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple read-only lookup without an output schema, the description names the returned fields and default limit, covering most invocation concerns. It doesn't document alternatives or failure cases, but these are not essential for this low-complexity tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Only _apiKey is described in the schema (33% coverage), so the description carries the burden. It adds meaning for take ('up to ... default 20') and steam_account_id ('by Steam account id'), which meaningfully compensates for bare schema entries.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Uses specific verb 'Fetch' and identifies exact resource: top heroes played by a Dota 2 player, keyed by Steam account id and ranked by match count. This distinguishes it from sibling tools like hero/heroes, which address broader hero data, and player, which targets account-level data.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Description implies the intended scenario — get a player's most-played heroes — but provides no explicit when-to-use or exclusions relative to siblings like player_matches or hero_stats. There is no guidance for choosing between this and player/heroes.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Several tools have overlapping or intentionally duplicated purposes: ask_pipeworx/ask_pipeworx_beta currently behave identically, and the Polymarket cluster (bet_research, polymarket_arbitrage, polymarket_edges, polymarket_fill_risk, polymarket_kalshi_spread) presents multiple scanners with fuzzy boundaries. The long descriptions help, but the set as a whole is hard to navigate without close reading.
Naming is a mix of bare single nouns (hero, match, meta, remember, forget), snake_case verb-first names (ask_pipeworx, compare_entities, generate_llms_txt), and noun-first compounds (pipeworx_feedback, bet_research, scan_competitor_ai_presence). There is no consistent verb_noun or noun-verb convention across the set.
At 43 tools, the server bundles at least five unrelated domains (Dota 2 stats, Pipeworx data querying, Polymarket analytics, memory, subscriptions, AI visibility). That is far too many for a focused MCP server, and the mix makes the surface feel like a grab bag rather than a purpose-built toolkit.
Each subdomain individually has solid coverage: Dota 2 has heroes/matches/players/tournaments/meta plus a GraphQL fallback, the data layer has discovery + routing + grounding + validation, and memory/subscriptions have full lifecycle operations. The only real gap is cohesion across domains; within each slice there are no obvious dead ends.