[PLAY] Hidden easter eggs placed in the 3D world at /world. Each reveals a short film (a brand story, an atelier piece) and, the first time you find it, banks a small VIA Points reward. These are content, never products, never for sale. Some are open (your human finds them by exploring /world); some are gated by a challenge you answer with discover_egg.
| Name | Required | Description | Default |
|---|---|---|---|
| agent_wallet | Yes | Your agent wallet address on Base |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure. It describes the game mechanic (banking VIA Points on first find) but does not clarify the tool's own behavior—whether it returns a list, modifies state, or triggers rewards. The description could mislead an agent into thinking calling the tool yields points, as it states eggs bank points rather than clarifying that finding them (not retrieving them) does.
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 concise, two sentences, and front-loaded with the core concept. Every sentence adds value—context, differentiation, and game mechanics—with no filler.
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 tool that retrieves world eggs, the description explains the context and types of eggs but omits what the tool actually returns (e.g., list of eggs, status, locations). Since there's no output schema, the description should clarify the return behavior. It provides necessary background but is incomplete for a full understanding.
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 only parameter, agent_wallet, is fully described in the schema with type and pattern, and the description doesn't mention it. Schema coverage is 100%, so the baseline of 3 applies; the description adds no additional parameter semantics.
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 focuses on what world eggs are (hidden content, some open, some gated) rather than explicitly stating the tool's action, but the name 'get_world_eggs' combined with the description and the reference to 'discover_egg' for gated challenges makes it clear that this tool retrieves egg information. It distinguishes from sibling discover_egg.
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 that discover_egg is used for gated challenges, but it doesn't explicitly say when to use this tool vs alternatives. There's no clear 'use this when you need to list eggs' or 'do not use for...' guidance, leaving usage somewhat implied.
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.
Several tool pairs could be confused, such as get_offers vs get_redemption_offers, get_world_eggs vs discover_egg, and the human vs agent purchase flows (initiate_purchase/confirm_purchase vs initiate_agent_purchase/confirm_agent_purchase). The descriptions are detailed and mostly disambiguating, but the presence of a retired tool (create_concierge) and multiple similarly named status/check tools add ambiguity.
The vast majority of tools follow a snake_case verb_noun pattern (list_drops, submit_design, redeem_points, verify_world_id). Minor deviations include 'priscilla_post' (proper noun prefix) and the interchangeable use of get/check/verify for status-like tools, but the overall convention is consistent and readable.
With 44 tools, the server is well above the 25-tool threshold that makes a surface feel heavy. Even though the platform covers many domains (commerce, affiliate, design, quests, concierge, marketing), this many tools strains discoverability and agent decision-making.
The buyer and designer flows are well covered (search → detail → purchase → download; brief → submit → status), but the brand side is incomplete. register_brand promises the ability to create briefs and product listings, yet no tools exist to create briefs or products, and there are no update/delete/refund operations for any resource, leaving registered brands at a dead end.