Skip to main content
Glama

Search works

search_works
Read-onlyIdempotent

Search the Klavierstuck catalogue of classical keyboard works, like the site's Works page. Combine free text (title words or a catalogue reference such as "BWV 846" or "Op. 28") with filters given in plain words: composer, key, sub-genre, instrument, performing forces, and a difficulty range on one scale. A name that matches nothing or several entries returns an error listing candidates. Each row has its klavierstuck.org URL and slug (pass it to get_work for details); the answer gives the total count and the sources to cite.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "search_works"
  }
}

Input Schema

NameRequiredDescriptionDefault
keyNoKey, in English in plain words, e.g. "D minor", "E-flat major" or "F♯ minor".
pageNoPage number, from 1.
limitNoWorks per page: 20 by default, at most 50 (larger values are capped).
queryNoFree text: words of the title or a catalogue reference, e.g. "nocturne" or "Op. 9".
forcesNoPerforming forces in plain words, e.g. "Solo", "Four hands" or "Two pianos".
composerNoComposer in plain words, e.g. "Chopin" or "Clara Schumann".
sub_genreNoSub-genre, in English in plain words, e.g. "Nocturne", "Waltz" or "Fugue".
instrumentNoInstrument in plain words, e.g. "Piano", "Organ" or "Harpsichord".
difficulty_maxNoHighest level on difficulty_scale (inclusive).
difficulty_minNoLowest level on difficulty_scale (inclusive).
difficulty_scaleNoDifficulty scale the range applies to in plain words, e.g. "PianoSyllabus" (0–10), "RCM", "ABRSM" or "PianoLibrary".

Schema Changelog

Changes observed during successful MCP inspections.

  1. 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 read-only, idempotent, non-destructive search, and the description adds useful behavior: ambiguous or empty name matches return an error listing candidates. It also discloses that each row contains a URL and slug, and that the answer includes total count and sources to cite. It does not cover pagination behavior in prose, but the schema does.

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?

The description is front-loaded with the core action and then adds only operationally useful details: filter combination, ambiguity errors, row identifiers, and citation information. There is no repetitive or empty wording, and each sentence contributes to correct invocation or interpretation.

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 an 11-parameter search tool with no output schema, the description covers the search model, filter behavior, error handling, return identifiers, and citation output well. It does not explain pagination or default page size in prose, though those are covered in the schema, so it is strong but not entirely complete.

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 schema already documents all 11 parameters with examples and constraints. The description adds conceptual context about combining free text with filters and applying a difficulty range on one scale, but most parameter meaning is already supplied by the schema. A baseline 3 is appropriate.

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 gives a specific verb and resource: search the Klavierstuck catalogue of classical keyboard works. It distinguishes the tool's role as a catalogue search and explicitly points to get_work for fuller details, so an agent can understand its place among the siblings.

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 clearly explains that free-text queries can be combined with plain-word filters such as composer, key, sub-genre, instrument, forces, and difficulty range. It also names get_work as the next step when a result's slug is available, though it does not explicitly state when a different sibling listing tool would be preferable.

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.

Resources