Skip to main content
Glama

Crawlora MCP

hltb_search

Read-only

Search HowLongToBeat's public game catalogue and return one page of results: total, page, page_total, page_size, and each game's id, name, alias, type, release year, platform, popularity, aggregate review score, the four play-style completion-time aggregates (main, main_plus_extras, completionist, all_styles) in seconds with sample counts, and the public aggregate counters. Mirrors the site's own POST /api/search/site request. The site protects that JSON endpoint with a short-lived token minted by /api/search/site/init; this tool mints the token with the qualified profile, uses it immediately and refreshes it once on a 403, never logging or persisting it. All filters are the site's own controls: platform, genre, perspective, flow and year multi-selects (each with an include/exclude mode), sort and length-range categories, a min/max hour range, modifiers and the Game Pass toggle. Every accepted value is served by hltb_filters. An empty q returns the site's catalogue browse (all games). No user, review, list or account data is returned; every time is a community estimate, not a guarantee.

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": "hltb_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
qNoOptional free-text game search terms, e.g. zelda. Empty returns the site's catalogue browse.
flowNoComma-separated flow values from hltb_filters flows
pageNo1-based result page; default 1.
sizeNoResults per page, 1-25; default 20.
sortNoSort category value from hltb/filters sort_categories; default popular.
yearNoComma-separated release years from hltb_filters years
genreNoComma-separated genre values from hltb_filters genres
modifierNoModifier value from hltb/filters modifiers.
platformNoComma-separated platform values from hltb_filters platforms
game_passNoApply the site's Game Pass toggle.
max_hoursNoOptional maximum length in whole hours.
min_hoursNoOptional minimum length in whole hours.
perspectiveNoComma-separated perspective values from hltb_filters perspectives
range_categoryNoLength range category from hltb/filters range_categories; default main.

Output Schema

NameRequiredDescriptionDefault
dataYesThe tool result payload (shape varies per tool; see each tool's docs resource).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior5/5

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

Goes well beyond the readOnlyHint/openWorldHint annotations: it discloses the mirrored upstream endpoint, a short-lived token minted from /api/search/site/init, single retry on 403, and no logging or persistence of the token. It also pre-empts data expectations by stating no user/account data is returned and that times are community estimates.

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 purpose and return payload, then filters, then caveats — a sensible order. It is a dense single paragraph with some low-value implementation detail (the exact init endpoint path) that an agent cannot act on, costing a little tightness.

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 14-parameter tool with nested filter objects, the definition covers the return shape, filter provenance, edge case (empty q), auth/token behavior, and data-scope limits. An output schema exists, so the payload enumeration is a bonus rather than a required burden.

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 adds real meaning the schema lacks: the multi-selects (platform, genre, perspective, flow, year) each carry an include/exclude mode, the hour filters are a min/max whole-hour range, and game_pass is the site's own toggle. It does not enumerate the mode string values themselves, leaving that to hltb_filters.

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?

Opens with a specific verb and resource ("Search HowLongToBeat's public game catalogue and return one page of results") and enumerates the returned fields, so an agent can distinguish it from sibling catalogue/value tools like hltb_filters without opening a schema.

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?

Gives clear operating context: every accepted filter value must come from hltb_filters, and an empty q deliberately falls back to catalogue browse. It does not explicitly route away to hltb_game or hltb_popular for single-game detail or popularity rankings, so sibling selection is only partly covered.

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