DraftCall

Player comparisons are in the DraftCall app

compare_players

Read-onlyIdempotent

Returns NO comparison. Head-to-head player comparisons and start or sit verdicts are available only in the free DraftCall app for iPhone and Android, and this tool answers every call with the download links and nothing else: no stats, no higher scorer, no pick. For facts about one player, use get_player.

Input Schema

Name	Required	Description
`player_a`	No	Ignored. Kept so older clients still validate.
`player_b`	No	Ignored. Kept so older clients still validate.
`scoring_format`	No	Ignored.

Output Schema

Name	Required	Description
`url`	Yes	The draftcall.io page these figures came from. This is the citation to use.
`message`	Yes
`available`	Yes	Always false. This server does not compare players.
`refreshed_at`	Yes	When this dataset was last refreshed, as an ISO 8601 timestamp.
`stats_season`	Yes	The completed NFL season every figure in this result describes.
`app_store_url`	Yes
`google_play_url`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed20 schema fields changedOct 12, 2026

changedInput schema / properties / player_a / description

Previous value: -"First player name, e.g. \"Bijan Robinson\"."New value: +"Ignored. Kept so older clients still validate."

changedInput schema / properties / player_b / description

Previous value: -"Second player name, e.g. \"Jahmyr Gibbs\"."New value: +"Ignored. Kept so older clients still validate."

removedInput schema / properties / scoring_format / default
```
Removed value: -"half_ppr"
```

changedInput schema / properties / scoring_format / description

Previous value: -"Scoring format. ppr awards 1 point per reception, half_ppr 0.5, standard 0. Defaults to half_ppr, the most common league setting."New value: +"Ignored."

removedInput schema / properties / scoring_format / enum

Removed value: -[
-  "ppr",
-  "half_ppr",
-  "standard"
-]

removedInput schema / required

Removed value: -[
-  "player_a",
-  "player_b"
-]

addedOutput schema / properties / app_store_url
```
Added value: +{
+  "type": "string"
+}
```

addedOutput schema / properties / available

Added value: +{
+  "description": "Always false. This server does not compare players.",
+  "type": "boolean"
+}

addedOutput schema / properties / google_play_url
```
Added value: +{
+  "type": "string"
+}
```

removedOutput schema / properties / higher_ppg

Removed value: -{
-  "description": "Name of the higher scorer, or null when the two are level.",
-  "type": [
-    "string",
-    "null"
-  ]
-}

addedOutput schema / properties / message
```
Added value: +{
+  "type": "string"
+}
```

removedOutput schema / properties / player_a

Removed value: -{
-  "properties": {
-    "byeWeek": {
-      "type": [
-        "integer",
-        "null"
-      ]
-    },
-    "efficiency": {
-      "description": "Per-game and per-target rates. Each is null where its inputs do not apply.",
-      "type": "object"
-    },
-    "gamesPlayed": {
-      "type": "integer"
-    },
-    "name": {
-      "type": "string"
-    },
-    "position": {
-      "description": "QB, RB, WR, TE, K or DEF.",
-      "type": "string"
-    },
-    "ppg": {
-      "description": "Points per game in each scoring format.",
-      "properties": {
-        "half_ppr": {
-          "type": "number"
-        },
-        "ppr": {
-          "type": "number"
-        },
-        "standard": {
-          "type": "number"
-        }
-      },
-      "required": [
-        "ppr",
-        "half_ppr",
-        "standard"
-      ],
-      "type": "object"
-    },
-    "rank": {
-      "description": "Rank within the position, by points per game.",
-      "type": "integer"
-    },
-    "slug": {
-      "description": "URL segment for this player on draftcall.io.",
-      "type": "string"
-    },
-    "stats": {
-      "description": "Season totals for the fields that apply to the position.",
-      "type": "object"
-    },
-    "team": {
-      "description": "Team abbreviation.",
-      "type": "string"
-    },
-    "url": {
-      "type": "string"
-    }
-  },
-  "required": [
-    "rank",
-    "name",
-    "position",
-    "team",
-    "ppg",
-    "gamesPlayed"
-  ],
-  "type": "object"
-}

removedOutput schema / properties / player_b

Removed value: -{
-  "properties": {
-    "byeWeek": {
-      "type": [
-        "integer",
-        "null"
-      ]
-    },
-    "efficiency": {
-      "description": "Per-game and per-target rates. Each is null where its inputs do not apply.",
-      "type": "object"
-    },
-    "gamesPlayed": {
-      "type": "integer"
-    },
-    "name": {
-      "type": "string"
-    },
-    "position": {
-      "description": "QB, RB, WR, TE, K or DEF.",
-      "type": "string"
-    },
-    "ppg": {
-      "description": "Points per game in each scoring format.",
-      "properties": {
-        "half_ppr": {
-          "type": "number"
-        },
-        "ppr": {
-          "type": "number"
-        },
-        "standard": {
-          "type": "number"
-        }
-      },
-      "required": [
-        "ppr",
-        "half_ppr",
-        "standard"
-      ],
-      "type": "object"
-    },
-    "rank": {
-      "description": "Rank within the position, by points per game.",
-      "type": "integer"
-    },
-    "slug": {
-      "description": "URL segment for this player on draftcall.io.",
-      "type": "string"
-    },
-    "stats": {
-      "description": "Season totals for the fields that apply to the position.",
-      "type": "object"
-    },
-    "team": {
-      "description": "Team abbreviation.",
-      "type": "string"
-    },
-    "url": {
-      "type": "string"
-    }
-  },
-  "required": [
-    "rank",
-    "name",
-    "position",
-    "team",
-    "ppg",
-    "gamesPlayed"
-  ],
-  "type": "object"
-}

removedOutput schema / properties / ppg_margin
```
Removed value: -{
-  "type": "number"
-}
```

removedOutput schema / properties / same_tier

Removed value: -{
-  "description": "True only when both play the same position and land in the same tier.",
-  "type": "boolean"
-}

removedOutput schema / properties / scoring_format
```
Removed value: -{
-  "type": "string"
-}
```
removedOutput schema / properties / shared_bye
```
Removed value: -{
-  "type": "boolean"
-}
```

removedOutput schema / properties / tier_a

Removed value: -{
-  "description": "The tier this player sits in at his position, or null when he is outside the ranked pool.",
-  "properties": {
-    "label": {
-      "type": "string"
-    },
-    "tier": {
-      "type": "integer"
-    }
-  },
-  "type": [
-    "object",
-    "null"
-  ]
-}

removedOutput schema / properties / tier_b

Removed value: -{
-  "description": "The tier this player sits in at his position, or null when he is outside the ranked pool.",
-  "properties": {
-    "label": {
-      "type": "string"
-    },
-    "tier": {
-      "type": "integer"
-    }
-  },
-  "type": [
-    "object",
-    "null"
-  ]
-}

changedOutput schema / required

Previous value: -[
-  "scoring_format",
-  "player_a",
-  "player_b",
-  "higher_ppg",
-  "ppg_margin",
-  "shared_bye",
-  "same_tier",
-  "url",
-  "stats_season",
-  "refreshed_at"
-]New value: +[
+  "available",
+  "message",
+  "app_store_url",
+  "google_play_url",
+  "url",
+  "stats_season",
+  "refreshed_at"
+]

First observedSep 1, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds real behavioral value beyond them: it discloses that parameters are inert and that the response body contains only download links, with no stats or scoring. It does not restate anything the annotations contradict.

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?

The critical fact — 'Returns NO comparison' — is front-loaded, followed by the explanation and the alternative in one compact block. No sentence is wasted; each clause (what it returns, what it doesn't, where the real data lives) earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present and all three parameters documented at 100% coverage, the description needn't explain return values or parameter formats. It fully discharges its remaining duty: telling the agent this tool cannot fulfill comparison requests and where to go instead.

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 is explicitly marked 'Ignored', so the schema already carries the semantics. The description reinforces this ('answers every call with... nothing else') but adds no format or syntax detail beyond the schema. Baseline 3 is appropriate.

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 immediately and unambiguously states what happens on every call: it returns NO comparison and answers with download links only. It distinguishes itself from the sibling get_player by naming it, so an agent knows this tool is a dead end for comparison data and must not expect stats.

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 states the condition under which this tool is useful (never, for the actual data) and explicitly routes the agent to an alternative: 'For facts about one player, use get_player.' The exclusion is explicit rather than inferred, which is exactly the routing an agent needs.

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

All DraftCall 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.