Skip to main content
Glama

Axad

Save to my cards

save_cards

Save flash cards to the learner's bag: words, phrases, idioms, sentences or patterns they engaged with, at or just above their level. Takes 1 to 6 cards a call, each with its front, back and the sentence where it was met; a card already in the bag gets the new example. Returns the saved and skipped cards and the bag's count and limit.

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": {
      "cards": "<cards>"
    },
    "name": "save_cards"
  }
}

Input Schema

NameRequiredDescriptionDefault
cardsYes
materialNoThe lesson the cards come from, when there is one.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / cards / items / properties / kind / description
      Previous value: -"word, phrase, pattern, concept, rule, exception, tip."New value: +"One of: word (one word, in its dictionary form), phrase (a fixed group of words whose meaning comes from its words: a collocation or set expression, \"een afspraak maken\"), idiom (a fixed expression whose meaning does not come from its words, \"iets onder de knie hebben\"), sentence (a whole sentence or clause with its verb, kept as met), pattern (a structure with open slots, \"om … te\"), rule (how a part of the grammar works), exception (a form that breaks a rule), concept (a named idea of the language or its culture: a split verb, de/het), tip (a way to learn or to pass the exam). Choose the most specific one that fits. A whole sentence or clause with its verb is a sentence, never a phrase; a phrase or idiom is a unit smaller than that. A fixed group whose meaning you get by reading its words is a phrase; one whose meaning you cannot get from its words is an idiom. Another word only if none fits."
  2. Changed1 schema field changed
    • changedInput schema / properties / cards / items / properties / image / description
      Previous value: -"A library picture id, or the concept of a nominate_image call."New value: +"A library picture id, or the concept a picture was requested under."
  3. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare this is a write operation (readOnlyHint=false) that is non-destructive and not idempotent. The description adds behavior the annotations cannot convey: the 6-card cap, the deduplication rule that 'a card already in the bag gets the new example,' and the fact that saved and skipped cards are returned along with the bag's count and limit. Permissions or failure modes (e.g., what happens when the bag is full) are not spelled out, keeping it below a 5.

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?

Three dense but purposeful sentences: purpose and content scope first, then the call-size and duplicate behavior, then the return shape. No filler, and the most important constraint is front-loaded.

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 takes on the burden of explaining returns (saved cards, skipped cards, bag count and limit), and it covers mutation side effects such as updating an existing card's example. The main omission is what triggers a skip and what happens at the bag limit, which matters for a non-idempotent write.

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?

Top-level schema coverage is only 50%, but the nested card properties (key, back, kind, lang, front, image, example) are each thoroughly documented in the schema, so the description's 'front, back and the sentence where it was met' mostly restates it. The genuinely additive semantic is the duplicate-handling rule and the implicit notion that a card is matched by something other than its surface text, but that matching key is never named.

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 opens with a specific verb+resource ('Save flash cards to the learner's bag') and enumerates the content types accepted (words, phrases, idioms, sentences, patterns), which distinguishes it from read-oriented siblings like search_bag or browse_catalog. An agent knows exactly what this tool produces without inspecting the 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?

It gives concrete selection criteria — cards should come from language the learner 'engaged with, at or just above their level' — and states the per-call batch bound of 1 to 6. It stops short of naming an alternative tool or an explicit when-not-to-use condition, so it is strong context without full routing guidance.

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.