Skip to main content
Glama

search

Read-onlyIdempotent

Search across Zindies creators, creations (zines), places (shops/venues), and events by keyword. Use query for the keyword and optional type to restrict to one resource. The response is always an object keyed by resource (creators / creations / places / events); with a single type, only that key is present. limit_per_type caps each list.

Places and events carry area (the JP region slug, null when unknown) and events kind. To go from one hit to the wider list, pass them to list_events (area, kind); get_event / get_place return the event lists a hit appears in (zones), and list_followable_zones every list.

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"
  }
}

Input Schema

NameRequiredDescriptionDefault
typeNoRestrict to one resource type. 'all' returns every type.all
queryYesSearch keyword. Searches name/title/description and translations (multi-locale).
localeNoResponse language for translatable text fields (names, titles, descriptions). Pass the language the user is conversing in when it is one of the supported locales. Fields without a translation fall back to their source language. Default: ja.
limit_per_typeNoMax items per resource type. Default 6 (max 24) when type=all; default 20 (max 50) for a single type.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already establish this as a safe, idempotent read with no side effects, so the description is free to spend its words on behavior it uniquely reveals: the response is always an object keyed by resource, and with a single `type` only that key appears. That keyed-response contract is genuinely useful and not derivable from annotations. It does not discuss result ordering or pagination beyond the per-type cap.

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?

The core contract (what it searches, how to restrict, what comes back) is front-loaded in the first sentence and a half, with follow-up traversal notes relegated to a second paragraph. The final clause about `area`, `kind`, and `zones` is more compressed than it needs to be, packing three cross-references into one sentence.

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 four-parameter multi-resource search with no output schema, the description covers the essentials: the resource set, the narrowing parameter, the keyed response shape, and the per-type limit. What it omits is how hits are matched and ordered and what an empty result looks like, which an agent may still want when presenting search results.

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 query, type, locale, and limit_per_type are all already documented in the schema, and the description mostly restates them ('Use `query` for the keyword'). It adds real value only for the single-`type` case, where it clarifies that only one key appears in the response. Baseline 3 is appropriate when the schema does the heavy lifting.

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 first sentence states a specific verb and scope: 'Search across Zindies creators, creations (zines), places (shops/venues), and events by keyword', and even glosses the domain jargon (zines, shops/venues). It is clearly distinguishable from the get_*/list_* siblings, which are described later as follow-up detail endpoints rather than keyword search.

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 explains how to narrow results ('optional `type` to restrict to one resource') and routes the agent onward, telling it to pass `area`/`kind` to list_events and to use get_event/get_place/list_followable_zones for the wider lists. It never explicitly states when NOT to use this tool (e.g., prefer get_creator when you already have an ID), so guidance is strong but not exhaustive.

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