Skip to main content
Glama
Sign In

Koboshi

by app.koboshi
OverviewDiscussionsAdmin

Save many words from this conversation

save_words
Idempotent

Adds several DIFFERENT words, phrases or idioms to the user's own Koboshi vocabulary in one request, for example a set of words from earlier in this conversation, sent together rather than one at a time. One word belongs in save_word, including a word wanted in more than one language. Each entry carries the language that word is written in. Words already in the vocabulary are reported as skipped; words new to Koboshi come back listed as needing a card, and cards sent with the first call are used straight away. Up to 50 items a call; a long phrase counts more than one of the account's 100-word daily limit, one word for every 10 words it holds. This connector can see only the current conversation.

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": {
      "words": "<words>"
    },
    "name": "save_words"
  }
}

Input Schema

NameRequiredDescriptionDefault
cardsNoOne card per word, written from Koboshi's card rules. Send them with the first call when you already have the rules; otherwise the result lists which words still need one and you send those next. A card for a word Koboshi already knows is ignored, so sending extras is harmless.
wordsYesThe words, phrases or idioms to save, at most 50 items. Each item is the word plus, when known, the language it is written in. A long phrase counts more than one toward the account's daily limit, one word for every 10 words it holds.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / words / items / properties / learning_language / enum
      Previous value: -[
-  "en",
-  "es",
-  "ja",
-  "de",
-  "ko",
-  "zh",
-  "ur",
-  "hi",
-  "pt",
-  "fr",
-  "it",
-  "ru",
-  "nl",
-  "tr",
-  "vi",
-  "fil",
-  "bn",
-  "nb",
-  "ar",
-  "id",
-  "th"
-]New value: +[
+  "en",
+  "es",
+  "ja",
+  "de",
+  "ko",
+  "zh",
+  "ur",
+  "hi",
+  "pt",
+  "fr",
+  "it",
+  "ru",
+  "nl",
+  "tr",
+  "vi",
+  "fil",
+  "bn",
+  "nb",
+  "ar",
+  "id",
+  "th",
+  "kk",
+  "fa"
+]
  2. Changed2 schema fields changed
    • changedInput schema / properties / words / description
      Previous value: -"The words to save, at most 50. Each item is the word plus, when you know it, the language THAT word is in."New value: +"The words, phrases or idioms to save, at most 50 items. Each item is the word plus, when known, the language it is written in. A long phrase counts more than one toward the account's daily limit, one word for every 10 words it holds."
    • addedInput schema / properties / words / items / properties / word / description
      Added value: +"The word, phrase or idiom, in its own language."
  3. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already cover safety (readOnly=false, destructive=false, idempotent=true, openWorld=false), yet the description still adds real behavioral depth: duplicate words are reported as skipped, new words come back flagged as needing a card, pre-supplied cards are consumed immediately, and the daily-limit accounting rule (a phrase consumes one word per 10 words toward the account's 100-word limit). This is disclosure well beyond the annotation set and is consistent with idempotentHint.

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?

Front-loaded with purpose and alternative routing, then behavior. Dense rather than padded, though the phrase-counts-toward-daily-limit rule is stated twice (in the description and again in the words schema entry), which is mild redundancy.

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?

There is no output schema, so the description carries the return-value burden — and it does, explaining both outcomes (skipped duplicates, words listed as needing a card). Combined with the batch limit, card-timing rule, and the connector's conversation-only visibility note, an agent has everything needed to call this correctly.

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%, so the baseline is 3; the description reinforces but does not go far beyond the schema. It does clarify cross-parameter behavior the schema cannot express (cards for already-known words are ignored, extra cards are harmless; long phrases consume multiple limit units), which is why it holds at 3 rather than lower.

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 ('Adds several DIFFERENT words, phrases or idioms to the user's own Koboshi vocabulary in one request') and explicitly routes the singular case to a named sibling: 'One word belongs in save_word'. An agent can separate this from save_word without opening either schema.

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?

Gives an explicit decision rule (this tool for sets from the conversation, save_word for a single word), plus the card-submission timing ('send them with the first call... otherwise the result lists which words still need one') and the batch bound ('Up to 50 items a call'). When-to-use and the alternative are both spelled out.

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

All Koboshi toolsInspect
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.

Resources