Skip to main content
Glama
io.github.christianclaudio/espn

io.github.christianclaudio/espn

Teams Search

teams_search
Read-onlyIdempotent

Search ESPN’s entity index by name to find athlete, team, or league IDs; set type to 'team' for teams, otherwise it searches athletes.

Instructions

Search ESPN's entity index by name to find an athlete ID, team ID, or league. Set type='team' for team names such as 'San Francisco 49ers'; type defaults to 'player', so omitting it searches athletes. For a team's games on a particular date, use the scoreboard tool directly when it is available, since it needs no team ID; otherwise use this search for the team ID. Returns IDs and display names for follow-up team or athlete tools.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "teams_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
typeNoEntity kind to search: 'player' for athletes, 'team' for team names, or 'league' for leagues. Defaults to 'player'; set this to 'team' when searching for a team.player
limitNo
queryYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv2.3.0
    • addedInput schema / properties / type / description
      Added value: +"Entity kind to search: 'player' for athletes, 'team' for team names, or 'league' for leagues. Defaults to 'player'; set this to 'team' when searching for a team."
  2. First observedv1.2.9

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, openWorld, and non-destructive, so safety is covered structurally. The description adds genuinely useful behavior: the implicit default of type='player' (a silent filtering behavior an agent would otherwise miss) and the fact that results are IDs/display names intended for follow-up calls.

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?

Three sentences, front-loaded with the core action, then the type default, then the sibling routing advice. Every sentence carries information; the only slight redundancy is restating the type='team' guidance already present in the schema.

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?

Given no output schema, the description usefully states what is returned and how it feeds other tools, and it explains the team-ID pathway. The remaining gap is the undocumented limit parameter for a search tool where result count matters.

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 only 33% (only type is described in the schema), so the description should compensate more. It reinforces type='team' semantics but largely repeats the schema's type description, and it never explains the 'limit' parameter (default 5) or clarifies whether 'query' matches names only, though 'by name' weakly implies it.

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 names a specific verb and resource ('Search ESPN's entity index by name') and states the output artifact (athlete ID, team ID, or league). It is clearly distinguishable from siblings such as teams_get_team, which needs an ID this tool produces.

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?

It explicitly covers when to use this tool ('set type="team" for team names'), what the default does ('type defaults to "player", so omitting it searches athletes'), and names an alternative plus its condition ('for a team's games on a particular date, use the scoreboard tool directly... otherwise use this search for the team ID').

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