Skip to main content
Glama

Find related audiobooks

find_related_books
Read-onlyIdempotent

Find other public audiobooks in the same target language as a given book: the books its reader page recommends. Optionally narrow them to a learner's CEFR level (or the nearest level that has books).

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": {
      "book_id": "<book_id>"
    },
    "name": "find_related_books"
  }
}

Input Schema

NameRequiredDescriptionDefault
levelNoThe learner's CEFR level (a1..c2), to prefer books at it.
book_idYesThe book's id (the `id` field of a Book).

Output Schema

NameRequiredDescriptionDefault
itemsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • addedOutput schema / $defs / Book / properties / audio_pattern
      Added value: +{
      +  "description": "Which languages the audio speaks for each sentence pair, in order, e.g. \"source-target-source\". \"source-only\" books are not translated: they speak only the source language and every target_text is empty.",
      +  "title": "Audio Pattern",
      +  "type": "string"
      +}
    • changedOutput schema / $defs / Book / properties / target_language / description
      Previous value: -"Content-language code the text was translated into."New value: +"Content-language code of the language being learned: the translation's language, or the source language for a book that is not translated (audio_pattern \"source-only\")."
    • changedOutput schema / $defs / Book / required
      Previous value: -[
      -  "id",
      -  "title",
      -  "author",
      -  "source_language",
      -  "target_language",
      -  "level",
      -  "audience",
      -  "origin",
      -  "duration_seconds",
      -  "speed_percent",
      -  "score",
      -  "published_at",
      -  "urls"
      -]New value: +[
      +  "id",
      +  "title",
      +  "author",
      +  "source_language",
      +  "target_language",
      +  "audio_pattern",
      +  "level",
      +  "audience",
      +  "origin",
      +  "duration_seconds",
      +  "speed_percent",
      +  "score",
      +  "published_at",
      +  "urls"
      +]
    • changedOutput schema / $defs / BookUrls / properties / language_hub / description
      Previous value: -"The page listing every public book in the book's target language. Null for a language without one."New value: +"The page listing every public book in the book's target_language. Null for a language without one."
  2. Changed2 schema fields changed
    • removedInput schema / $defs
      Removed value: -{
      -  "Level": {
      -    "description": "CEFR difficulty level of a book, easiest first. `d1` is the rung above C2 (expert register); a learner's own level is one of a1..c2.",
      -    "enum": [
      -      "a1",
      -      "a2",
      -      "b1",
      -      "b2",
      -      "c1",
      -      "c2",
      -      "d1"
      -    ],
      -    "title": "Level",
      -    "type": "string"
      -  }
      -}
    • changedInput schema / properties / level / anyOf
      Previous value: -[
      -  {
      -    "$ref": "#/$defs/Level"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "enum": [
      +      "a1",
      +      "a2",
      +      "b1",
      +      "b2",
      +      "c1",
      +      "c2",
      +      "d1"
      +    ],
      +    "type": "string"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
  3. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already establish read-only, idempotent, non-destructive, closed-world behavior, so the bar is lower. The description still adds real value beyond them: results are restricted to public books, restricted to the same target language, sourced from the reader page's recommendations, and the level filter degrades gracefully to 'the nearest level that has books' rather than returning empty.

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 tight sentence, front-loaded with the core action and resource, followed by a colon-apposition that defines 'related' precisely. Every clause earns its place, and no wording is redundant.

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?

For a 2-parameter read tool with full schema coverage, an output schema, and rich annotations, the description covers what matters: scope, relation source, and the fallback semantics of the optional filter. It does not mention result count limits or ordering, which is the only remaining gap an agent might care about.

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?

Schema coverage is 100%, so a baseline of 3 would be defensible. However, the description adds semantics the schema does not carry: 'level' is the learner's CEFR level and the filter is a preference with fallback behavior when an exact level has no books, which changes how an agent should interpret empty results. book_id semantics are left to the schema, which documents them adequately.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource ('Find other public audiobooks'), plus scope constraints: same target language as the given book, and the source of the relation ('the books its reader page recommends'). This is far more precise than a generic 'find related' phrasing. It does not explicitly contrast itself with siblings like search_books or get_book, so it lands just short of the top score.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied: call this when you already have a book_id and want adjacent recommendations in the same language, optionally filtered by level. The optional narrowing and its fallback are mentioned, but there is no explicit 'use X instead when Y' guidance relative to search_books or get_book.

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.