goldseam

Playlist Policy Save

playlist_policy_save

Save one school's policy after the server checks it. Every source is a capture_file that playlist_policy_open named and a quote of 300 characters or fewer copied verbatim from that capture's cleaned text; the quote check is exact, with no fuzzy matching. The server also checks that every course code is one of the school's CourseShelf learning units, every award_title appears in the award_types section, and every min_credits is a positive number. It never alters the policy. It returns policy_id, status, and every error in plain words: a policy with errors is saved as rejected, so correct it and save again.

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": {
      "unitid": "<unitid>",
      "built_by": "<built_by>",
      "policy": "<policy>"
    },
    "name": "playlist_policy_save"
  }
}

Input Schema

Name	Required	Description
`policy`	Yes
`unitid`	Yes	The school, by its IPEDS UNITID
`built_by`	Yes	Who built this policy: a short string naming the agent and model. Stored with the saved policy. A save without it is rejected.

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedNov 10, 2026

addedInput schema / properties / built_by

Added value: +{
+  "description": "Who built this policy: a short string naming the agent and model. Stored with the saved policy. A save without it is rejected.",
+  "examples": [
+    "claude-opus chat",
+    "openai gpt build-agent"
+  ],
+  "type": "string"
+}

addedInput schema / properties / policy / properties / designations / items / properties / abbreviation

Added value: +{
+  "description": "Optional: the designation's printed abbreviation, exactly as printed. The designation's quote must contain its name or this abbreviation.",
+  "examples": [
+    "SI"
+  ],
+  "type": [
+    "string",
+    "null"
+  ]
+}

changedInput schema / required

Previous value: -[
-  "unitid",
-  "policy"
-]New value: +[
+  "unitid",
+  "built_by",
+  "policy"
+]

AddedNov 10, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Goes well past the annotations (readOnlyHint=false, destructiveHint=false, idempotentHint=false) by disclosing that the server validates before writing, that it 'never alters the policy', that failed policies are still written as rejected, and exactly what the response carries. The rejection-on-error behavior is a non-obvious trait an agent would otherwise misjudge.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Five tight sentences, front-loaded with purpose then validation rules then return/retry behavior. No sentence is redundant and each one carries a constraint or a behavior the caller needs.

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 correctly explains the return (policy_id, status, plain-word errors). It covers validation and the retry path for a nested, three-parameter write tool; the only gap is what happens on re-save of an identical policy, which idempotentHint=false hints at but the text never resolves.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Adds real meaning beyond the 67%-covered schema: capture_file must match the name playlist_policy_open used, quotes must be ≤300 characters copied verbatim from cleaned text with exact (non-fuzzy) matching, course codes must resolve to CourseShelf learning units, award_title must appear in the award_types section, and min_credits must be positive. unitid and built_by are left to the schema, so not a full 5.

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?

States a specific verb and resource ('Save one school's policy') plus the governing condition ('after the server checks it'), and ties the inputs back to the sibling that produces them ('a capture_file that playlist_policy_open named'). An agent can distinguish this from playlist_policy_open and the other playlist_* tools 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?

Gives a clear operating context: the save is validated, a policy with errors is persisted as rejected, and the agent should 'correct it and save again' — an explicit retry loop. It stops short of naming alternatives (e.g. when to use playlist_save or get_policy instead), so no exclusions are stated.

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

All goldseam tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.