For browser game makers: check a game, free listing link, Boost plans, checkout links. Read-only.
Scored across 3 tools
The three tools target distinct intents: status lookup, boost plan pricing, and generating a free listing link. However, check_game partially overlaps with get_listing_link, since check_game already returns the free listing link when a game isn't listed, which could cause some selection confusion.
All three names follow a consistent snake_case verb_noun pattern (check_game, get_boost_options, get_listing_link). The minor verb variation between 'check' and 'get' is semantically meaningful and not confusing.
Three tools is slightly thin for a creator-focused platform but reasonable given each covers a distinct step (status, listing, boosting). It stays well-scoped rather than padding with redundant operations.
The surface is entirely read-only by design, generating links rather than performing actions, which is a legitimate scope. Still, there are notable gaps: no way to confirm a game went live after listing, no boost purchase/status tracking, and no account or analytics view for creators.
Looks up a browser game on Foundplay by its play link, Foundplay page link or slug. Says whether it's listed, and if so its page, public play and upvote counts, whether its link works, whether its maker has claimed it, and whether it can be boosted, with the links to claim or boost it. If it isn't listed, gives the free link that lists it. Read-only.
| Name | Required | Description | Default |
|---|---|---|---|
| game | Yes | The game's play link (where people play it), its Foundplay page link, or its Foundplay slug. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so "Read-only" at the end is redundant. However, with no output schema the description earns credit for disclosing exactly what comes back: listed status, page, play and upvote counts, link validity, maker-claim status, boost eligibility, and claim/boost links.
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?
The purpose and accepted inputs are front-loaded in the first sentence, and the return contents follow in one dense sentence. The trailing "Read-only" is pure repetition of the annotation and is the one wasted fragment.
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 read tool with no output schema, the description covers the essential behavioral surface by enumerating the response fields and the fallback behavior when the game is unlisted. It stops short of error/edge handling (invalid slug, ambiguous input), which keeps it from a 5.
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 100% and the single parameter's schema description already enumerates play link / page link / slug. The description repeats that same set without adding format, normalization, or ambiguity-handling detail, 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?
The description opens with a specific verb+resource ("Looks up a browser game on Foundplay") and immediately names the accepted identifiers (play link, Foundplay page link, slug). It is clearly the composite lookup tool versus the narrower siblings get_boost_options and get_listing_link, both of whose outputs it absorbs.
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 by the accepted input types (you call it when you have a game link or slug), but there is no explicit when-to-use/when-not statement and no mention of the siblings. An agent has to infer that get_boost_options and get_listing_link are for the narrower cases this tool already reports on.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Lists Boost, Foundplay's paid promotion: each plan's price, guaranteed plays, days and placements, how refunds work, and the free boost line. Given a game, also says whether it can be boosted and gives a checkout link for each plan. A person must open the link, sign in and pay on Stripe themselves. Read-only: nothing is bought by calling this.
| Name | Required | Description | Default |
|---|---|---|---|
| game | No | The game's play link (where people play it), its Foundplay page link, or its Foundplay slug. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, yet the description adds real context beyond them: the checkout link requires a human to open it, sign in and pay on Stripe, and nothing is purchased by the call itself. That clarifies the link is a handoff, not an automated transaction. No rate-limit or error behavior, but the key behavioral surprise is disclosed.
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?
Front-loaded with the primary verb and resource in sentence one, then the conditional game behavior. The closing 'Read-only: nothing is bought by calling this' slightly overlaps the earlier Stripe sentence, but the reinforcement is intentional and cheap.
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?
With no output schema, the description must carry the return-value burden, and it does: it enumerates price, guaranteed plays, days, placements, refunds, free boost line, boostability and checkout links. For a static read-only plan listing, little is missing; only exact response shape/format is unspecified.
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 is fully documented as a play link, Foundplay page link, or slug. The description only restates 'Given a game' and notes the conditional boostability output; it adds no format, matching or validation detail beyond the schema. 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?
States a specific verb (Lists) and resource (Boost plans / paid promotion) and enumerates the exact contents: price, guaranteed plays, days, placements, refunds, free boost line, plus conditional boostability and checkout links. An agent can distinguish this from check_game and get_listing_link without opening any schema.
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 ('Given a game, also says whether it can be boosted') but the description never states when to call this versus the siblings check_game or get_listing_link, nor any exclusions or prerequisites. Adequate but leaves the routing decision to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
For a browser game's play link, returns the foundplay.io link that lists it for free, with the form filled in, plus what happens next and free ways to get players. If the game is already listed, returns its page instead. Listing needs the person to sign in with their email; the game goes live right away. Read-only: nothing is listed until the person publishes.
| Name | Required | Description | Default |
|---|---|---|---|
| playUrl | Yes | Where people play the game, starting with https://. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly/idempotent/non-destructive, but the description adds real value beyond them: sign-in with email is required, the game goes live immediately, and nothing is actually listed until the person publishes. That is genuine side-effect and prerequisite disclosure.
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?
Four sentences, front-loaded with the primary return value, then the conditional branch and prerequisites. Slightly dense and the 'for free, with the form filled in' clause is a bit tangled, but every sentence carries 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?
With no output schema, the description must convey the return shape, and it does loosely ('the link, plus what happens next and free ways to get players'). Combined with the auth prerequisite and the read-only clarification, an agent has enough to invoke it correctly.
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 100% with a single well-described parameter, so the baseline is 3. The description adds only that the input is a 'browser game's' play link, a marginal clarification over the schema's own 'Where people play the game, starting with https://.'
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 and resource: given a browser game's play link, it returns the foundplay.io listing link pre-filled. It also distinguishes the already-listed branch from the new-listing branch, though it never names the sibling tools (check_game, get_boost_options).
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?
It gives implied usage context ('For a browser game's play link') and describes the alternate branch when the game is already listed, but it never states when to prefer this over check_game or get_boost_options. Usage must be inferred from the scenario description.
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.
check_gameget_boost_optionsget_listing_linkPublish, fork, improve browser games. No-auth reads; OAuth to post. Wheel: verified ops knowledge.
Build, publish and update browser games with saves, leaderboards and realtime multiplayer built in.
Publish, play-test and fix HTML5 browser games from your AI assistant. Own address, 70% ad share.
Videogames MCP — wraps Free-to-Play Games API (freetogame.com, free, no auth)
Add one secure layer between your agents and this server.