Run a prompt on a GPU model tier: 'chat' (fast 7B, ~$0.0015), 'llama' (budget 8B, ~$0.0008), 'reason' (35B, ~$0.004), 'think' (deep chain-of-thought 35B MoE, ~$0.004), 'code' (coder model, ~$0.0025), or 'kaspa-expert' (RAG-grounded, current Kaspa knowledge, ~$0.0015). Returns the completion text.
| Name | Required | Description | Default |
|---|---|---|---|
| tier | No | chat | |
| prompt | Yes | ||
| system | No | ||
| max_tokens | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description must fully disclose behavior. It mentions GPU execution and approximate costs but omits key operational details like error handling, statefulness, rate limits, or authentication requirements. The return type is vaguely 'completion text' without structure.
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 verbose paragraph that mixes action, tier details, and costs. While front-loaded with the verb, it could be more concise by structuring as a bulleted list. Each sentence provides information but the density reduces readability.
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?
Given the parameter count (4), lack of output schema, and no annotations, the description covers the main functionality and tier options. However, it lacks guidance on system prompt behavior, max_tokens limits, and error handling. It is adequate for simple use but incomplete for advanced scenarios.
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 coverage is 0%, so the description must compensate. It adds significant value by enumerating valid 'tier' values (chat, llama, reason, think, code, kaspa-expert) with associated capabilities and costs. However, parameters 'system' and 'max_tokens' are not explained, and 'prompt' lacks format details.
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 action 'run a prompt' and the resource 'GPU model tier', listing specific model names (chat, llama, etc.) and explicitly says 'Returns the completion text'. This distinguishes it from sibling tools like classify or embed_text.
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 provides model tier details with cost estimates, guiding which tier to pick for different tasks (fast, budget, reasoning, code). It implies usage for text generation but does not explicitly exclude when not to use or compare to alternatives beyond listing sibling tool names.
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, with detailed descriptions that prevent ambiguity. Even within related domains (e.g., covenant operations, proving steps), the functions are well-separated and described.
Most tools follow a verb_noun or noun_noun pattern with underscores, but there are some single-verb names like 'catalog' and 'classify'. Within subdomains naming is consistent (e.g., kaspa_*, covenant_*, prove_*). Minor deviations prevent a perfect score.
36 tools is on the high side for a typical MCP server, but the broad scope (blockchain, payments, ZK proving, text processing, search, registry) justifies the count. It borders on being too large for easy navigation but remains reasonable.
The server covers a wide range of functionalities with no critical gaps for its stated domain. Minor gaps exist (e.g., no direct Kaspa send transaction tool), but the covenant tools provide a workaround. Overall, the surface is fairly complete.