Discover third-party MCP servers published in Coinbase CDP's Bazaar. Read-only. Filter by free-text q and/or network.
| Name | Required | Description | Default |
|---|---|---|---|
| q | No | Free-text filter matched against the server JSON | |
| limit | No | Max rows (default 25, max 100) | |
| cursor | No | Pagination cursor | |
| network | No | Filter by network, e.g. 'base' |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden for behavioral disclosure. It explicitly states 'Read-only,' which is a key behavioral trait. However, it does not mention pagination behavior (e.g., how limit/cursor work), result format, or edge cases like empty results, which would be useful for a discovery tool. The presence of 'Read-only' is positive, but other behavioral aspects remain undisclosed.
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 extremely concise: two short sentences plus 'Read-only.' It is front-loaded with the core purpose, then adds the key safety trait and filter options. Every sentence earns its place with no fluff or redundancy.
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 read-only discovery tool with 4 parameters, all described in the schema, the description covers the essential purpose, read-only nature, and filter mechanics. The lack of an output schema and annotations means the description could explain return format or pagination, but the presence of limit/cursor in the schema partially compensates. It is nearly complete but not fully comprehensive, missing explicit statement of what the tool returns.
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?
Input schema coverage is 100%, so baseline is 3. The description adds minimal semantic value beyond the schema by restating 'free-text q and/or network' as filters, but this paraphrases existing parameter descriptions. No additional meaning is provided for limit or cursor, so the description does not compensate beyond what the schema already offers.
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: 'Discover third-party MCP servers published in Coinbase CDP's Bazaar.' It uses a specific verb ('discover') and resource ('MCP servers'), and the scope ('published in Coinbase CDP's Bazaar') distinguishes it from sibling tools like bazaar_discover_resources, which targets resources rather than servers.
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 usage by stating it is read-only and filtering options ('Filter by free-text q and/or network'), but it does not explicitly provide when-to-use vs alternatives or any exclusions. Sibling tools are not referenced, so the agent must infer from the name when this tool is appropriate rather than the description.
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 tools have overlapping purposes, such as mint_loyalty_tokens vs earn_points (both mint loyalty tokens with fee bundles), create_loyalty_program vs register_loyalty_program (deploy vs register existing token), and activate_loyalty_program vs update_program_status (both manage program status). Some pairs like check_voucher_status and list_gift_certificates also overlap on voucher/certificate tracking. However, descriptions are detailed enough to reduce ambiguity for careful agents.
Most tools follow a consistent verb_noun snake_case pattern (e.g., create_reward, list_loyalty_programs). Subtle deviations include earn_points vs mint_loyalty_tokens (different verbs for similar mint operations) and use_voucher vs redeem_reward (different verb styles for redemption). Overall, the naming is predictable and understandable.
With 39 tools, this server is bloated for a loyalty platform. The addition of Bazaar discovery/payment tools and report management expands the scope, but many tools overlap or cover minor variations (e.g., two workflow planners: generate_program_defaults and get_program_workflow_status). A leaner set of 20-25 tools would be more appropriate.
The tool surface covers the full loyalty program lifecycle: creation, activation, registration, token minting/transfer, rewards, gift certificates, vouchers, offers, customer export, analytics, and reports. Notable gaps include no CRUD for personalized offers (only create), no edit capability for rewards (only status changes), and no direct function to list all vouchers by merchant (only status check by code). These are minor workarounds.