search_bazaarFREE. Search the public Coinbase x402 Bazaar catalog for Base paid APIs at or below MAX_PRICE_USD, then cache matches for call_x402_api.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max results to return (default 10) | |
| query | Yes | Semantic or text search query, for example weather or token balance |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses that the tool is free and that it caches matches, which is a side effect. However, it omits other behavioral traits like rate limits, authentication requirements, or whether the operation is read-only. For a tool with no annotations, this is moderate but incomplete coverage.
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, front-loaded sentence that wastes no words. It begins with the cost note 'FREE' and immediately states the purpose and side effect, making it efficient and easy to parse.
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 should hint at return behavior, but it only says 'cache matches' without stating what is returned. The constant MAX_PRICE_USD is mentioned without explanation, which could confuse agents. It is adequate for a simple search tool but leaves gaps regarding output format and the price cap.
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?
Both parameters (limit and query) have descriptions in the schema, covering 100% of parameters, so the baseline is 3. The tool description adds no additional meaning to the parameters beyond what the schema already states—it does not clarify query semantics or limit behavior further.
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 searches a public catalog for paid APIs under a price cap and caches results for call_x402_api. It names the specific resource (Coinbase x402 Bazaar), the action (search), and the filtering criterion (price), distinguishing it from sibling list tools like list_discovered_apis and list_verified_apis.
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 its role as a precursor to call_x402_api by stating it caches matches for that tool, which signals when to use it. However, it does not explicitly contrast with alternatives or state when not to use it, such as when you want all APIs regardless of price.
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.
The core dispatcher tools are distinct, but the 84 auto-discovered wrappers contain dozens of near-identical news, weather, and translation endpoints. An agent cannot reliably tell many of these apart without reading provider-specific details, and misselection is likely.
Core tools use a readable verb_noun pattern, but most tools are machine-generated `x402_<domain>_<path>_<number>` names with opaque numeric suffixes. The two naming schemes are mixed, and the generated names are not intuitive.
95 tools is an extreme mismatch for a coherent MCP surface. The bulk are auto-registered third-party proxies that duplicate the same few categories, creating massive prompt bloat and selection overhead.
For an x402 dispatcher, the core lifecycle is well covered: discovery, search, quote, route-and-call, stats, paywall status, and cashflow/P&L. Minor gaps such as no deregistration or detailed per-transaction drill-down exist, but main workflows do not dead-end.