Buy per-query access to live data listings — first taste free via data_preview. Listing: exploitdb: Exploit-DB — New Public Exploits & PoCs (0.01 USDC/query). Returns fund instructions after data_session_open.
| Name | Required | Description | Default |
|---|---|---|---|
| session_id | Yes | UUID of a data session you opened (from data_session_open). |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
注释已声明只读、幂等、非破坏性。描述额外揭示了工具返回资金指令而非直接执行交易，并给出了具体定价，这些都有助于代理理解调用效果。
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?
描述由三句构成，分别覆盖核心动作、具体列表和返回行为，信息密度高且没有冗余。核心动词“Buy”和资源位于句首，方便代理快速理解。
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?
给定单参数、简单模式、完整注释和一个明确的输出说明，描述已覆盖调用所需的关键信息。未解释的资金指令格式属于次要细节。
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?
输入模式覆盖率为100%，session_id已有详细说明。描述未增加额外的参数语义，因此维持基线3分。
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?
描述以明确的动词“Buy”和资源“per-query access to live data listings”开头，并具体指定了列表（exploitdb）和价格（0.01 USDC/query），使其与data_preview、data_session_fund等兄弟工具清晰区分开。
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?
描述提供了明确的使用顺序：在data_session_open之后使用，并提及data_preview作为免费品尝的替代方案。虽然没有显式排除其他情况，但对于这类简单工具，上下文已足够引导代理。
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 overlap in purpose: data_session_fund, data_session_funding_package, and data_session_attach_escrow all concern funding/escrow; a2awire_guide, get_recommended_action, and onboard_start all provide guidance/state; and discover_agents, find_paid_work, and hire_and_execute all point at marketplace hiring. Descriptions help, but the boundaries between these clusters are still easy for an agent to misjudge.
Most tools follow a readable snake_case verb_noun pattern such as data_session_open, discover_agents, and verify_contract. There are minor deviations like a2awire_guide, data_session_funding_package, and register, but the overall convention is fairly consistent.
16 tools is at the borderline heavy end, and many tools belong to a generic A2AWire marketplace/onboarding layer rather than the Exploit-DB data-access purpose. The count is not extreme, but the server feels over-scoped for what should be a focused per-query data listing.
The Exploit-DB flow covers preview, open, fund, attach escrow, and query, but there are notable dead ends: find_paid_work tells you to call start_job, and get_recommended_action references start_admission, yet neither tool exists. There is also no explicit withdraw/close-session tool, leaving the lifecycle incomplete.