Retrieve a Dota 2 team's hero pool with games played, wins, and win rate, sorted by games played; unknown team IDs return not found.
OpenDota Dota 2 team hero pool. Returns the heroes a team has played with games, wins and win rate, sorted by games played. Heroes the team never played are omitted. An unknown team id returns not found.
| Name | Required | Description | Default |
|---|---|---|---|
| team_id | Yes | Positive OpenDota team ID from opendota-teams or a match response |
Changes observed during successful MCP inspections.
v1.17.18Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the behavioral burden and does well: it discloses the sort order (games played), the shaping rule (heroes never played are omitted), and the error behavior (unknown team id returns not found). What it omits is read-only confirmation, rate-limit or pagination behavior, and the raw vs. aggregate nature of the response, which keeps it from a 5.
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?
Four short sentences, front-loaded with what the tool returns, followed by sort order, then the omission rule and error case. No filler and no repetition of the tool name as though it were an explanation.
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 single-parameter read tool with no output schema and no annotations, everything an agent needs is present: the returned fields, the ordering, which heroes are excluded, and what happens on a bad id. The description effectively stands in for the missing output schema.
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?
Schema coverage is 100% and the schema already documents team_id as a positive OpenDota team ID sourced from opendota-teams or a match response. The description only adds the failure mode for an invalid id, so baseline 3 applies — the schema does the heavy lifting and nothing new about the id's format or origin is contributed.
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?
States a specific verb and resource ('Returns the heroes a team has played') plus the exact metrics returned (games, wins, win rate). The phrase 'team hero pool' plus the omission rule makes it clearly distinct from siblings like opendota_team_players, opendota_team_matches, and opendota_heroes without needing to name them.
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?
Usage is only implied: 'team hero pool' suggests you call it when you want a team's hero history, but there is no explicit when-to-use, no pointer to opendota_teams for obtaining the id, and no named alternative such as opendota_team_matches for match-level detail. The 'unknown team id returns not found' note is a useful edge case but is about failure, not tool selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.