Skip to main content
Glama

Search shared decks

search_shared_decks
Read-only

Search AnkiWeb’s shared deck catalogue by title, then sort and page all returned matches without needing an AnkiWeb session. Use it to find shared decks before downloading or inspecting them.

Instructions

Search AnkiWeb's shared deck catalogue by title. AnkiWeb returns every match at once, so the results are sorted and paged here. Needs no AnkiWeb session. AnkiWeb rate-limits searches to about four a minute, and a refused address can stay refused for over an hour while get_shared_deck and download_shared_deck keep working; repeating a search within ten minutes is served from cache. The notes, audio and images counts are AnkiWeb's own, and audio and images have been seen at 0 for a deck whose sample notes carry both.

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_shared_decks"
  }
}

Input Schema

NameRequiredDescriptionDefault
pageNo
sortNorating is thumbs up minus thumbs down; modified is newest first.rating
limitNo
queryYesWords to look for in deck titles.

Output Schema

NameRequiredDescriptionDefault
pageYes
queryYes
totalYes
hasMoreYes
resultsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.0.2

TDQS

A3.9/5.0
Behavior4/5

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

Adds substantial behaviour beyond the readOnlyHint/openWorldHint annotations: no AnkiWeb session required, ~4 searches/minute rate limit, a refused address staying refused for over an hour while sibling tools keep working, and a 10-minute result cache. The only caveat is that the final sentence about audio/image counts hints at return-value details an output schema may already cover.

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-loads purpose then stacks high-value operational facts; each sentence carries unique information, though the closing data-quality sentence is the least essential and could be trimmed.

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 annotations and an output schema present, the description covers the risky unknowns well (rate limits, caching, auth-free access). It falls slightly short on guiding pagination and follow-up tool choice for a search-then-fetch workflow.

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 coverage is 50%, with page and limit undocumented in the schema; the description only says results are "sorted and paged here" without explaining page size, limits, or what the sort options mean beyond the schema's own enum note. It justifies why paging exists but adds little operational meaning.

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 ("Search AnkiWeb's shared deck catalogue") plus the matching scope ("by title"), which separates it from get_shared_deck and download_shared_deck named later.

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 context is implied by the catalogue-search framing, but there is no explicit routing advice such as when to follow up with get_shared_deck or download_shared_deck, or when to prefer browsing one's own decks via list_my_decks.

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