Free, ad-free open-source browser games that open and play right inside the chat.
The last two health checks of this connector failed. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.
If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.
Scored across 4 tools
Each tool has a distinct purpose: discovering new arrivals (new_games), browsing/searching the catalog (show_arcade), launching a specific game (play_game), and recording a rating (rate_game). The only mild overlap is between new_games and show_arcade, since both surface game listings, but the 'recently added vs. browse/filter' distinction in the descriptions is clear enough.
Three tools follow a clear verb_noun pattern (play_game, rate_game, show_arcade), and new_games is a slight deviation as an adjective_noun phrase rather than a verb. Still readable and predictable, with no mixed casing styles.
Four tools is compact but fits a simple arcade server where the whole domain is discover, browse, play, and rate. Every tool earns its place; it sits just under the comfortable range but is not thin enough to feel incomplete on scope alone.
The core loop (discover -> browse -> play -> rate) is covered, but there are notable gaps: no way to retrieve a game's details/metadata without launching it, no way to remove or modify an existing rating, and no view of top-rated or user-rated games. Agents can work around some of this via show_arcade search, but not the rating lifecycle.
Show the games added to AGENTPARK most recently (new games arrive twice a day).
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful context beyond that — the refresh cadence ('new games arrive twice a day') — but says nothing about result count, ordering, or pagination behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single front-loaded sentence with no waste; the freshness cadence is packed into a parenthetical rather than a second sentence.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a parameterless read-only listing with no output schema, the description covers what the tool returns at a conceptual level. A hint about result volume or ordering would make it fully complete, but nothing essential is missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. The description correctly does not invent parameter behavior.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb (show) and resource (games added to AGENTPARK most recently), which an agent can distinguish from play_game and rate_game. It does not explicitly contrast itself with show_arcade, so sibling differentiation is only implied.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The purpose implies the use case (browsing newly added games), but there is no explicit when-to-use guidance, no mention of when to prefer show_arcade instead, and no prerequisites or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Open one AGENTPARK game ready to play, by its name or slug.
| Name | Required | Description | Default |
|---|---|---|---|
| game | Yes | Game name or slug, e.g. "Snake Pro" or "skifree" |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds that a game is returned 'ready to play,' but it doesn't say what 'open' produces (a link, session, or launch payload) or what happens if the name/slug doesn't match.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
One short sentence with the action front-loaded and zero filler; nothing could be removed without losing information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a one-parameter tool with annotations and no output schema, the description is nearly sufficient, but the verb 'open' leaves the return behavior ambiguous — an agent cannot tell whether it receives a playable URL, a session handle, or an error on unknown input.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% and the single 'game' parameter already carries an example. The phrase 'by its name or slug' restates the schema rather than adding format or matching rules beyond it, so baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Specific verb+resource: 'Open one AGENTPARK game ready to play, by its name or slug.' It clearly differs from show_arcade (browse) and rate_game (feedback) by emphasizing opening a single game ready to play, though it never names those siblings explicitly.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Usage is implied — an agent infers this is the tool for launching a specific game rather than listing games or rating them — but there is no explicit when-to-use versus when-not guidance and no sibling is referenced.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Record the user's 1-5 star rating for an AGENTPARK game. Only call when the user gives a rating.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes | ||
| stars | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare a non-readonly, idempotent, non-destructive operation, so the safety profile is covered. The description adds no behavioral context beyond the call trigger — it doesn't say whether an existing rating is replaced, what happens with an unknown slug, or what the result looks like. With annotations present the bar is lower, so a 3 fits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two short sentences, zero filler, with the core action stated first and the call constraint second.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple two-parameter mutation with no output schema and annotations covering safety, the definition is nearly sufficient. The remaining gap is what happens on a duplicate or invalid slug, which the idempotentHint partially covers.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description carries the burden. It restates the 1-5 range for stars (matching the schema bounds) and implies slug identifies an AGENTPARK game, but never says what a slug is or what format it takes. Partial compensation only.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb (record) and resource (a 1-5 star rating for an AGENTPARK game), which is clearly distinct from siblings like play_game and show_arcade. It doesn't explicitly name or contrast with those siblings, so it stops 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.
Does the description explain when to use this tool, when not to, or what alternatives exist?
'Only call when the user gives a rating' gives an explicit positive condition plus an exclusion, which is more than most definitions offer. No alternatives are named, but the trigger condition is unambiguous.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Show AGENTPARK: free open-source browser games that play well on a phone. Use when the user asks for AGENTPARK, the arcade, or a game to play or browse. Optional category filter (Puzzle, Arcade, Action, Racing, Strategy, Idle, Word & Math, 3D, Retro, 2-Player) or a search word.
| Name | Required | Description | Default |
|---|---|---|---|
| query | No | ||
| category | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds that the games are free, open-source and phone-friendly but says nothing about result shape, result count, or whether filtering is exact-match — modest added value over the annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three compact sentences: identity first, triggering condition second, parameter detail last. No filler and no repetition of the title.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a two-optional-parameter read tool with no output schema, the description covers what it returns conceptually (a set of games) and what the filters do. Missing only return-shape details (list format, counts, pagination), which is a minor gap for a simple catalog viewer.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, so the description carries the load and does so well: it enumerates all ten valid category values and clarifies that `query` is a free-text search word. It stops short of stating case sensitivity, exact-match behavior, or whether query and category combine.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description states a specific resource (AGENTPARK arcade catalog) and what it contains (free open-source browser games, mobile-friendly). It weakly distinguishes from siblings — browsing/listing versus new_games, play_game, rate_game — but never names them, so the agent must infer that this is the browse/listing entry point.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
'Use when the user asks for AGENTPARK, the arcade, or a game to play or browse' gives clear triggering conditions. No explicit when-not or named alternative (e.g. 'use play_game to launch a specific title'), so routing between siblings is left to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
rate_game1 field changedInput schema / properties / clientRemoved value: -{
- "type": "string"
-}new_gamesplay_gamerate_gameshow_arcadeReal, free browser games that open in the chat: city builder, racer, horde shooter, deckbuilder.
Create instant multiplayer browser-game rooms friends join from a link. No account or app needed.
Publish, play-test and fix HTML5 browser games from your AI assistant. Own address, 70% ad share.
Discover playable browser experiences and manage creator-owned game uploads on Arcade.fun.
Add one secure layer between your agents and this server.