Skip to main content
Glama

Admissions game: one reader

game_read
Read-only

App-only stage of admissions_game, called by the in-chat view, not by the model. One fictional admissions reader (the kind given) reads the student's application for this school and round and returns short notes: what works, what gave them pause, one fix, and the lines they marked. Simulation only; it never writes or rewrites essays.

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": {
      "kind": "<kind>",
      "school": "<school>",
      "application": "<application>",
      "run": "<run>"
    },
    "name": "game_read"
  }
}

Input Schema

NameRequiredDescriptionDefault
runYesThe run state returned by admissions_game (seating, readers and ids). Pass it back unchanged.
kindYesWhich reader on the committee reads this time.
majorNoIntended major, if the student gave one.
roundNoApplication round: "ED", "ED2", "EA", "REA" or "RD".
schoolYesThe college the application is for, as the student named it (e.g. "Tufts").
visitsNoAny campus visits or contact with the college the student mentioned.
applicationYesThe student's own application text (essays, activities, grades) exactly as they supplied it. Used for this run only; never stored.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changed
    • addedInput schema / properties / application / description
      Added value: +"The student's own application text (essays, activities, grades) exactly as they supplied it. Used for this run only; never stored."
    • addedInput schema / properties / kind / description
      Added value: +"Which reader on the committee reads this time."
    • addedInput schema / properties / major / description
      Added value: +"Intended major, if the student gave one."
    • addedInput schema / properties / round / description
      Added value: +"Application round: \"ED\", \"ED2\", \"EA\", \"REA\" or \"RD\"."
    • addedInput schema / properties / run / description
      Added value: +"The run state returned by admissions_game (seating, readers and ids). Pass it back unchanged."
    • addedInput schema / properties / school / description
      Added value: +"The college the application is for, as the student named it (e.g. \"Tufts\")."
    • addedInput schema / properties / visits / description
      Added value: +"Any campus visits or contact with the college the student mentioned."
  2. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare read-only, non-destructive, closed-world, and non-idempotent, so the bar is lower; the description still adds real value by enumerating the return shape and by disclosing the privacy contract ('used for this run only; never stored') and the simulation boundary ('never writes or rewrites essays'). It does not disclose cost, pacing, or why repeated calls differ (non-idempotent), which would be the remaining gap.

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?

Two sentences, front-loaded with the caller constraint, with no filler. It is fairly dense — the output list, simulation disclaimer, and no-write guarantee are packed into one sentence — which costs a point on scannability but nothing is wasted.

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?

With no output schema, the description carries the burden and does describe the returned notes (what works, what gave pause, one fix, marked lines). Combined with the 7-parameter nested schema and the privacy note, an agent has enough to call it correctly; only the variability of repeated calls (non-idempotent) is left implicit.

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 description coverage is 100% and every parameter including the nested run object and the kind enum is documented in the schema, so the baseline of 3 applies. The description adds no parameter-level detail beyond the schema — no explanation of how run ties to admissions_game state or how kind maps to committee readers.

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?

Names a specific verb and resource: one fictional admissions reader reads the student's application for a given school/round and returns notes (what works, what gave pause, one fix, marked lines). It also scopes itself against siblings by calling out that this is the app-only stage of admissions_game, so an agent can distinguish it from the parent orchestration tool without opening a schema.

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?

Explicitly states who calls it — 'called by the in-chat view, not by the model' — which is a strong usage exclusion, and ties it to the app-only stage of admissions_game. It stops short of naming what a model should call instead for reader feedback, so it lacks a complete alternative routing statement.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources