Flash

Study panel: archive

panel_archive

Idempotent

Used by Flash's study panel only; never call it yourself. Takes the card on screen out of study after the user tapped Archive (or puts it back on Undo) and returns the panel's next card.

Input Schema

TableJSON Schema

Name	Required	Description
`card_id`	Yes	The card on screen.
`archived`	Yes	True takes the card out of study; false puts it back (Undo).
`session_id`	Yes	The session the panel is showing.

Output Schema

TableJSON Schema

Name	Required	Description
`card`	No
`deck`	No	The session's deck and tags as asked for: the tags are the header's chips, and both let the panel start the session again after allowing more new cards; start only.
`goal`	No	The goal the session counted toward, once the queue is empty.
`tags`	No
`view`	Yes	Which of the panel's views this is: always `study`.
`week`	No	The seven study days after today and the cards due on each, once the queue is empty, for the finished screen's week.
`state`	Yes	`card` (one to show), `held` (today's limits hold the rest back), `caught_up` (nothing due), or `empty` (no cards in the scope at all).
`preload`	Yes	Signed links to warm: this card's back and the next card's front.
`ui_lang`	No	The language the account reads Flash in (`panel_lang`); start only.
`next_due`	No	When the next cards come, once the queue is empty.
`recorded`	Yes	False only from panel_grade, when the card had already been graded elsewhere (in the chat) and this grade was not recorded.
`reviewed`	Yes	Reviews recorded in this session so far, in the panel or the chat: with `remaining`, the panel's progress ("2 / 10").
`site_url`	Yes	The site's front page, for the finished screen's "Study on the web": the cards live there too.
`next_card`	No	The card expected after this one, its front only, so the panel can show it the moment a grade is tapped and record the grade behind it. The grade's own answer still says which card really comes.
`remaining`	Yes	Cards in the queue, this one included.
`deck_label`	No	The deck as the site shows it (`Cardio › ECG`), for the panel's header; start only.
`session_id`	Yes
`held_by_limit`	Yes	Cards today's limits hold back.
`reminders_offer`	No	Whether the finished screen offers reminders (panel_reminders): only once the queue is empty, and only when the server can send this account reminders it has not turned on.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 17, 2026

addedOutput schema / $defs / PanelGoalOut

Added value: +{
+  "description": "The goal a finished session counted toward, for the panel's finished\nscreen: the web's done-screen block, its words in the account's\nlanguage.",
+  "properties": {
+    "behind": {
+      "description": "Behind its plan: the ring in amber.",
+      "type": "boolean"
+    },
+    "caption": {
+      "description": "How much is learned, then the days left or how to catch up.",
+      "type": "string"
+    },
+    "catch_up": {
+      "description": "New cards \"Study N more\" adds to the deck today; 0 for no button.",
+      "format": "uint32",
+      "minimum": 0,
+      "type": "integer"
+    },
+    "deck": {
+      "description": "The deck the goal is on, as boost_new_today names it.",
+      "type": "string"
+    },
+    "head": {
+      "description": "\"On track for Dec 18\", \"15 cards behind for Dec 18\".",
+      "type": "string"
+    },
+    "percent": {
+      "description": "How much of the deck is learned, out of 100: the ring.",
+      "format": "uint32",
+      "minimum": 0,
+      "type": "integer"
+    },
+    "percent_label": {
+      "description": "The share learned as text (\"40%\"), shown when there is no button.",
+      "type": "string"
+    },
+    "study_more": {
+      "description": "The button's words.",
+      "type": "string"
+    }
+  },
+  "required": [
+    "deck",
+    "percent",
+    "behind",
+    "head",
+    "caption",
+    "percent_label",
+    "catch_up",
+    "study_more"
+  ],
+  "type": "object"
+}

addedOutput schema / properties / goal

Added value: +{
+  "anyOf": [
+    {
+      "$ref": "#/$defs/PanelGoalOut"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "description": "The goal the session counted toward, once the queue is empty."
+}

Changed2 schema fields changedOct 16, 2026

addedOutput schema / $defs / PanelCardOut / properties / front_lang

Added value: +{
+  "description": "The front's language, for its `lang`; absent when nothing says it.",
+  "type": "string"
+}

addedOutput schema / properties / ui_lang

Added value: +{
+  "description": "The language the account reads Flash in (`panel_lang`); start\nonly.",
+  "type": [
+    "string",
+    "null"
+  ]
+}

AddedOct 12, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false and idempotentHint=true; the description corroborates rather than contradicts these by framing the write as reversible (Undo restores the card) and by disclosing the return behavior ('the panel's next card'). It adds real context about call-site and reversibility, though not permissions or failure modes.

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?

A single dense sentence with the critical constraint ('never call it yourself') front-loaded, then the card state change, then the return value. Every clause 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?

An output schema exists so return values need not be enumerated, and all three parameters are fully described in the schema. For a panel-internal mutation tool, the description supplies all the context an agent needs, including the decisive instruction not to invoke it directly.

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% (card_id, archived, session_id each documented, including the true/false semantics of archived). The description adds no syntax or format detail beyond the schema, so the baseline 3 applies.

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 ('takes the card on screen out of study', 'puts it back on Undo') and scopes it to the study panel's on-screen card, which implicitly separates it from deck-level siblings like archive_deck and from delete_cards.

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 an unusually explicit usage boundary ('Used by Flash's study panel only; never call it yourself') plus the triggering condition (user tapped Archive / Undo). It does not name an alternative tool for agents who need a similar archive operation, so it stops just short of 5.

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

All Flash 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.