Forget one memory or a filtered set of memories for the current agent.
| Name | Required | Description | Default |
|---|---|---|---|
| game_id | No | ||
| preview | No | ||
| category | No | ||
| memory_id | No | ||
| older_than_days | No |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully disclose behavioral traits. It only states it 'forgets' (implies deletion), but does not clarify if deletion is permanent, requires special permissions, or affects other agents. The preview parameter behavior is not explained.
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 description is a single short sentence, which is concise but sacrifices important detail. Given the complexity of filtering parameters, the description is under-specified.
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 5 parameters, no schema descriptions, no annotations, and an output schema present but not described, the description is woefully incomplete. It fails to explain how filters combine (AND/OR), the role of the preview flag, and the default behavior when no parameters are provided.
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%, meaning the input schema provides no descriptions for any of the 5 parameters. The tool description adds no information about parameters, leaving their meaning entirely to inference from names. This is a critical gap.
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 clearly states the tool's purpose: forgetting one or a filtered set of memories for the current agent. It uses a specific verb ('forget') and resource ('memories'), and distinguishes itself from sibling tools like arcade_remember (store) and arcade_recall (retrieve).
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 description implies the tool is for erasing memories of the current agent, but provides no explicit guidance on when to use it versus alternatives (e.g., when to forget vs. update a memory). No exclusions or prerequisites are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool has a clearly distinct purpose: game actions, board interaction, chat, session management, memory, history, leaderboard, etc. No two tools overlap in functionality, making selection unambiguous.
All tools share the 'arcade_' prefix, but the pattern is not strictly verb_noun; some are single verbs (e.g., arcade_chat, arcade_wait) while others are noun_verb or verb_noun. However, names are descriptive and consistently formatted.
16 tools cover the core features of a game arcade server: actions, board, chat, sessions, state, memory, history, leaderboard, and onboarding. The scope is well-balanced, not overwhelming or sparse.
The tool surface covers essential game lifecycle and social features. Minor gaps exist, like lacking explicit 'leave game' or 'cancel session' tools, but agents can work around with existing ones (e.g., arcade_state, arcade_wait).