Skip to main content
Glama

Search browser games

search_games
Read-onlyIdempotent

Find browser games by player preferences. Returns at most 10 (default 3) ranked games with direct play links, match reasons and evidence labels. Strict filters never accept unknown facts; check "shortage" when fewer games match than requested.

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_games"
  }
}

Input Schema

NameRequiredDescriptionDefault
paceNorelaxed = "take your time": no clock or opponent rushing you (most puzzles, turn-based, solitaire-like); timed = reflexes or speed decide (arcade, real-time).
limitNoNumber of results (default 3, max 10).
queryNoFree-text preference, e.g. "relaxing space puzzle". Matched against title, genres, themes, keywords and description.
tonesNoMatch games having ANY of these tones/moods (funny, cute = cute/cozy, relaxing, scary, intense = intense/competitive, serious = serious/realistic...).
cursorNoOpaque pagination cursor from a previous response.
genresNoMatch games having ANY of these genres.
inputsNoGame must support ALL of these input methods.
no_adsNotrue = only games known to show no ads.
themesNoMatch games having ANY of these themes (setting/subject, e.g. fantasy = fantasy/epic, sci_fi = sci-fi/space, war = war/military, ocean = sea/pirates).
devicesNoGame must work on ALL of these devices. Use ["mobile"] for "works on my phone".
no_signupNotrue = only games known to be playable without creating an account.
publisherNoOnly games listed under this publisher id (as returned in a game's publisher.id).
subgenresNoMatch games having ANY of these sub-genres (the distributor's finer categories, e.g. hidden-object, match-3, tower-defense, jigsaw-puzzles).
art_stylesNoMatch games having ANY of these graphics styles (pixel = retro/pixel art, vector = flat/minimalist, hand_drawn = artsy/painterly). Inferred from screenshots.
difficultyNo
min_ratingNoOnly games whose average player rating (1-5 stars, one decimal) is at least this. Games with fewer than 3 ratings have no public rating and never match. Ratings are player opinions, not verified facts.
no_downloadNotrue = only games known to play in the browser without a download/install.
min_evidenceNoWeakest evidence accepted for filtered facts: inferred (default) < declared (by developer) < tested (by us).
offline_playNotrue = only games known to work offline after loading.
player_modesNoGame must support ALL of these modes. "same_device_multiplayer" = local multiplayer on one device.
free_to_startNotrue = only games known to be free or free to start.
session_lengthNoshort = a session fits in ~5 minutes; medium = 5–20; long = 20+.
include_unknownNotrue = also return games whose filtered facts are UNKNOWN, as a separate labelled list. They never count as matches.
min_graphics_polishNoOnly games whose graphics polish score is known and at least this (0–5; 3 = decent, consistent style; 4 = polished; 5 = outstanding). Scores are inferred from screenshots.

Output Schema

NameRequiredDescriptionDefault
resultsYes
shortageNo
next_cursorYes
min_evidenceYes
total_matchesYes
applied_filtersYes
unknown_matchesNoGames whose filtered facts are unknown. NOT matches.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • changedInput schema / properties / art_styles / items / enum
      Previous value: -[
      -  "pixel",
      -  "vector",
      -  "cartoon",
      -  "anime",
      -  "hand_drawn",
      -  "stylized_3d",
      -  "low_poly",
      -  "voxel",
      -  "realistic",
      -  "neon"
      -]New value: +[
      +  "pixel",
      +  "vector",
      +  "cartoon",
      +  "anime",
      +  "hand_drawn",
      +  "3d",
      +  "stylized_3d",
      +  "low_poly",
      +  "voxel",
      +  "realistic",
      +  "neon"
      +]
    • changedInput schema / properties / art_styles / maxItems
      Previous value: -10New value: +11
    • addedInput schema / properties / publisher
      Added value: +{
      +  "description": "Only games listed under this publisher id (as returned in a game's publisher.id).",
      +  "pattern": "^[a-z0-9][a-z0-9-]{0,79}$",
      +  "type": "string"
      +}
    • changedOutput schema / properties / results / items / properties / publisher / anyOf
      Previous value: -[
      -  {
      -    "additionalProperties": false,
      -    "properties": {
      -      "name": {
      -        "type": "string"
      -      },
      -      "verification": {
      -        "enum": [
      -          "inferred",
      -          "verified"
      -        ],
      -        "type": "string"
      -      }
      -    },
      -    "required": [
      -      "name",
      -      "verification"
      -    ],
      -    "type": "object"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "additionalProperties": false,
      +    "properties": {
      +      "id": {
      +        "type": "string"
      +      },
      +      "name": {
      +        "type": "string"
      +      },
      +      "verification": {
      +        "enum": [
      +          "inferred",
      +          "verified"
      +        ],
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "id",
      +      "name",
      +      "verification"
      +    ],
      +    "type": "object"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • changedOutput schema / properties / unknown_matches / items / properties / publisher / anyOf
      Previous value: -[
      -  {
      -    "additionalProperties": false,
      -    "properties": {
      -      "name": {
      -        "type": "string"
      -      },
      -      "verification": {
      -        "enum": [
      -          "inferred",
      -          "verified"
      -        ],
      -        "type": "string"
      -      }
      -    },
      -    "required": [
      -      "name",
      -      "verification"
      -    ],
      -    "type": "object"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "additionalProperties": false,
      +    "properties": {
      +      "id": {
      +        "type": "string"
      +      },
      +      "name": {
      +        "type": "string"
      +      },
      +      "verification": {
      +        "enum": [
      +          "inferred",
      +          "verified"
      +        ],
      +        "type": "string"
      +      }
      +    },
      +    "required": [
      +      "id",
      +      "name",
      +      "verification"
      +    ],
      +    "type": "object"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
  2. Changed1 schema field changed
    • addedInput schema / properties / pace
      Added value: +{
      +  "description": "relaxed = \"take your time\": no clock or opponent rushing you (most puzzles, turn-based, solitaire-like); timed = reflexes or speed decide (arcade, real-time).",
      +  "enum": [
      +    "relaxed",
      +    "timed"
      +  ],
      +  "type": "string"
      +}
  3. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent and closed-world, so the safety profile is covered. The description adds behavior the annotations cannot convey: the result cap (default 3, max 10), that results are ranked and carry play links, match reasons and evidence labels, and the important rule that strict filters never accept unknown facts, with a 'shortage' signal when the match count falls short.

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?

Three sentences, front-loaded with purpose, then return shape, then filtering semantics and the shortage cue; nothing is padded. It is dense and efficient, though the third sentence compresses two distinct ideas (strict unknown rejection and shortage handling) into one line.

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 24-parameter, zero-required search tool with an output schema and rich annotations, the description covers what the agent most needs: that it is a ranked preference search, the result cap, and how unknown facts and thin results are handled. Remaining gaps, such as whether to loosen filters or lower min_evidence before concluding no results exist, are minor given the schema breadth and output schema.

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 96%, so parameters are already well documented and the baseline applies. The sentence 'strict filters never accept unknown facts' adds useful cross-cutting meaning about how the boolean filters like no_ads, free_to_start and no_download behave, but it doesn't explain individual parameters such as min_evidence or include_unknown beyond what the schema states.

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?

The description opens with a specific verb and resource ('Find browser games') and scopes it to 'by player preferences', so the agent knows this is a preference-driven discovery search rather than a lookup. It doesn't explicitly contrast with the sibling get_game_details, but the search framing is unambiguous.

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?

It gives one concrete usage rule ('check "shortage" when fewer games match than requested'), which is genuinely actionable guidance about what to do with a thin result set. However, it says nothing about when to call this versus get_game_details, or about relaxing filters before giving up, so the when-to-use picture is only partially 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