Skip to main content
Glama

Search Library

search_library
Read-onlyIdempotent

RETURNS A LIST OF BOOKS (works on a topic) — NOT passages. PICK THIS to discover which works exist on a subject. → For quotable text use search_translations (exact words) or search_concept (by meaning); if the user already named an author/work, call get_book directly (or list_books to find the ID) — the AI summary + chapter outline is usually the right first answer. Searches titles, authors, subjects, and (as a secondary signal) translated text. Query tips: single distinctive words or short phrases work best ("memory palace", "ouroboros"); quoted phrases match exactly. Each result includes total_matches (full count) + returned (this page) + offset for pagination. FIRST ENGLISH TRANSLATIONS: pass first_translation=true to filter to books the catalogue flags as first English translations; each row carries is_first_translation. That flag is a researched claim and can be wrong (multi-work volumes especially); call get_book for the evidence and say "flagged as" rather than "is". To answer "do you hold X?" call check_duplicate, not this: a ranked list is not a holdings check.

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": {
      "query": "<query>"
    },
    "name": "search_library"
  }
}

Input Schema

NameRequiredDescriptionDefault
sortNo
limitNoMax results per page (default 10, max 100)
queryYesSearch query — prefer single distinctive concepts ("alchemy", "tree of life") over long natural-language phrases. Wrap in "double quotes" for exact phrase.
offsetNoPagination offset (use with limit to page through total_matches; default 0)
year_toNoPublication year range end
languageNoFilter by original language (e.g., Latin, German, Greek)
year_fromNoPublication year range start
has_translationNoOnly return books with translations
first_translationNoOnly books carrying the site's "First Translation" flag (the same filter as the website). A researched claim, not a proof; see get_book first_translation for status and hedging.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / first_translation
      Added value: +{
      +  "description": "Only books carrying the site's \"First Translation\" flag (the same filter as the website). A researched claim, not a proof; see get_book first_translation for status and hedging.",
      +  "type": "boolean"
      +}
  2. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already cover read-only/idempotent/non-destructive, but the description goes further: it explains the searchable fields (titles, authors, subjects, translated text as a secondary signal), the pagination contract (total_matches vs returned vs offset), and — most valuably — warns that is_first_translation is a fallible researched claim and prescribes hedging language plus verification via get_book. It does not discuss ranking behavior for the relevance sort or result size caps beyond the schema's limit.

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 the caps-locked core distinction, then alternatives, then field behavior, then query tips, then a final disambiguation — a deliberate and readable ordering. It is dense and every clause carries information, though the pagination sentence partly restates the offset/limit schema descriptions and could be trimmed.

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?

For a 9-parameter tool with no output schema, the description still tells the agent what a result row contains (total_matches, returned, offset, is_first_translation) and how to page through results. Combined with the routing guidance and the reliability caveat on the translation flag, an agent has everything needed to call it correctly and interpret the output.

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 89%, so the baseline is 3; the description earns an extra point by adding query syntax guidance beyond the schema (short distinctive phrases, quoted-phrase exact matching, example queries) and by expanding on first_translation with the multi-work-volume failure mode and the "flagged as" phrasing. The remaining parameters (sort, year_from/year_to, language, has_translation) get no narrative treatment, which keeps it below 5.

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 ("RETURNS A LIST OF BOOKS (works on a topic)") and immediately negates the most likely confusion ("NOT passages"). It explicitly differentiates itself from search_translations, search_concept, get_book, list_books, and check_duplicate, so an agent can route without opening any 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 positive selection criteria ("PICK THIS to discover which works exist on a subject"), named alternatives with the condition that selects each (quotable text → search_translations/search_concept; user already named a work → get_book; holdings question → check_duplicate), and an explicit when-not. Nothing is left to inference.

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.