Get player stats
get_player_statsSeason stats for one player on a team (points/assists/rebounds for NBA, passing/rushing/etc for NFL).
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| team | Yes | ||
| player | Yes | Player name, e.g. 'Jalen Brunson' or 'Mahomes' |
get_player_statsSeason stats for one player on a team (points/assists/rebounds for NBA, passing/rushing/etc for NFL).
| Name | Required | Description | Default |
|---|---|---|---|
| team | Yes | ||
| player | Yes | Player name, e.g. 'Jalen Brunson' or 'Mahomes' |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior. The description adds that results are season aggregates with per-league stat categories, which is useful but overlaps with purpose; it does not disclose side effects, auth requirements, or edge-case behavior. No contradiction with annotations.
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?
Single sentence, front-loaded with the core scope, followed by compact parenthetical examples. Every word contributes; no filler or repetition.
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, two-parameter lookup, the description plus annotations cover purpose and safety adequately. The only notable gap is an explicit team-format example; output details are lightly sketched through the stat categories, which is acceptable given no output schema and low complexity.
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 description coverage is 50%: player has an example, but team has none. The description clarifies that stats are for one player on a team and lists sport-specific stat types, but it does not specify what team values look like (e.g., city vs franchise name) or otherwise compensate for the bare team parameter.
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 resource and scope: season stats for one player on a team, with sport-specific stat categories. This clearly differentiates it from sibling tools like get_roster (players) and get_team_schedule (games), and the title verb 'get' is supported by the descriptive noun phrase.
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?
The description implies use for player stat lookups and indicates season-level data, but it never says when not to use it or names an alternative such as get_roster or list_teams. No explicit routing or exclusions are provided.
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.
Each tool targets a distinct resource: injuries, odds, player stats, roster, schedule, and the universe of teams. There is no overlap or ambiguity between them.
All tools use a clear verb_noun pattern: get_* for specific resources and list_teams for the full collection. This is consistent and predictable.
Six tools is well-scoped for a read-only sports data server covering NFL and NBA information. Each tool covers a meaningful slice of the domain without bloat.
The surface covers the main pre-game and season data needs: teams, rosters, schedule, stats, injuries, and odds. Only a minor gap exists for something like game results or standings, which is not central to the apparent betting/team-info focus.