gpufeed_recommend
Return a bounded lowest-observed-cost recommendation for further verification.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| gpu | Yes | ||
| count | No | ||
| hours | No |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Return a bounded lowest-observed-cost recommendation for further verification.
| Name | Required | Description | Default |
|---|---|---|---|
| gpu | Yes | ||
| count | No | ||
| hours | No |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden. It does not state whether the recommendation is deterministic, what 'bounded' means, whether results are cached/live, or how cost is defined. An output schema exists, so return values are covered, but the core behavior of the recommendation is opaque.
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?
A single sentence, so nothing is wasted, but it is under-specified rather than concise. 'Bounded lowest-observed-cost recommendation for further verification' packs jargon without front-loading a clear action or object.
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 3-parameter tool with no annotations and no requirement to explain outputs (output schema exists), the description should at least define the GPU input and the 'bounded' recommendation semantics. It leaves the agent unable to confidently invoke the tool or interpret the cost basis.
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 description coverage is 0% and the description adds nothing about any of the three parameters. 'gpu' is required but its expected format (model name? ID?) is undocumented, and 'count'/'hours' defaults are uninterpreted. With low coverage the description must compensate but instead says nothing.
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 verb 'recommend' and the vague resource 'lowest-observed-cost' are present, but the subject is never named — it never says it recommends GPUs, though the 'gpu' parameter and gpufeed_* siblings imply it. The phrase 'for further verification' obscures the actual output rather than clarifying it. It is distinguishable from gpufeed_get_cheapest only by the word 'recommend', which is not enough.
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?
No when-to-use, when-not-to-use, or alternative is mentioned, despite siblings like gpufeed_get_cheapest and gpufeed_compare_providers that an agent would obviously need to disambiguate against. The fragment 'for further verification' hints at a downstream workflow but gives no actionable selection guidance.
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.