Skip to main content
Glama
Sign In

Shipvo

by io.github.shipvo
OverviewDiscussionsAdmin

find_apps

Read-only

Search the Store by need, for example "split bills". Matches the query against app name, description and tags (case-insensitive, word based) and filters by country, language and currency when an app declares them; apps that declare nothing for a filter still match. Returns up to limit apps (default 10, max 25) with id, name, one-line description, version and whether it is installed, best match first. An empty list means nothing matched. Fails with store_unreachable when the marketplace cannot be reached (nothing is guessed). Install a result on the simulator with install_app, or on the person's own phone with request_app_install. Logged in device_log as simulated.

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": {
      "session": "<session>",
      "query": "<query>"
    },
    "name": "find_apps"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMost results to return (default 10, max 25)
queryYesWhat the person needs, for example "split bills"
countryNoCountry code, for example FR
sessionYesSession from open_app
currencyNoCurrency code, for example EUR
languageNoLanguage code, for example fr

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.4/5.0
Behavior5/5

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

Annotations already declare a safe read, yet the description adds substantial behavior: result fields returned, best-match ordering, the empty-list meaning, the named store_unreachable failure with the guarantee that nothing is guessed, and that the call is logged in device_log as simulated. These are exactly the traits an agent cannot infer from readOnlyHint.

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?

One tight paragraph, front-loaded with purpose and query semantics, then filters, then return shape, then failure mode, then next-step routing. Every sentence carries an actionable fact and none repeat structured data unnecessarily.

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 six-parameter read-only search with no output schema, the description covers interpretation of the query, soft-filter behavior, sizing, return contents and ordering, the empty result case, the failure mode, and follow-up tools. An agent has everything needed to call it correctly and interpret the response.

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 the baseline is 3, but the description contributes genuine meaning the schema lacks: the query matches name, description and tags case-insensitively and word-based, and filters are soft because apps declaring nothing for a filter still match. The limit default/max is repeated from the schema, but the filter fallback rule is valuable and non-obvious.

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?

States a specific verb and resource ("Search the Store") plus how the query is interpreted ("by need"), which an agent can distinguish from a plain listing tool. It never names a sibling such as list_store_apps or list_apps to sharpen the contrast, so it lands short of a 5.

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?

The closing sentence explicitly routes the agent onward: install_app for the simulator, request_app_install for the person's own phone. That is real when-to-use-this-vs-another guidance for the follow-up step, though there is no explicit statement of when to prefer find_apps over list_store_apps.

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

All Shipvo toolsInspect
Try in Browser
Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources