list_gpusList the GPU models GPU Finder tracks: canonical name and slug, VRAM, memory type, bandwidth, interconnect, provider and instance counts, and min/max hourly USD price. Returns canonical GPU identifiers and hardware specifications. Pages default to 20 rows, maximum 100; each page costs one data unit.
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | Pagination. Omit for the first page. |
Changes observed during successful MCP inspections.
Input schema / properties / page / descriptionAdded value: +"Pagination. Omit for the first page."Input schema / properties / page / properties / cursor / descriptionAdded value: +"nextCursor from the previous page. Reuse the same filters and limit."Input schema / properties / page / properties / limit / descriptionAdded value: +"Rows per page, 1-100. Defaults to 20."Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, non-destructive, closed-world, so the safety profile is covered. The description adds genuinely new context beyond annotations: page size defaults and caps, cursor-based paging, and the cost model ("each page costs one data unit") — a rate-limit-style disclosure the agent cannot get from structured fields.
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?
Three tight sentences: identity of the resource first, return contents second, operational paging/cost constraints last. No redundancy or filler, and every clause carries information an agent needs.
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?
There is no output schema, so the description must carry the return shape — and it does, naming identifiers, VRAM, memory type, bandwidth, interconnect, provider/instance counts, and min/max hourly USD price. Combined with paging and cost disclosure, an agent has everything needed to call this correctly.
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 100%, including descriptions for limit and cursor, so the schema does the heavy lifting and baseline 3 applies. The description restates the 20/100 pagination bounds and adds that page count drives data-unit cost, but contributes no new meaning about the cursor or filter semantics.
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?
States a specific verb and resource ("List the GPU models GPU Finder tracks") and immediately enumerates the fields returned, so the agent knows exactly what comes back. The resource is clearly distinct from sibling tools like list_providers and get_prices, so no confusion is possible.
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?
Usage is implied — browse the GPU catalog — but the description never states when to prefer this over get_prices, get_availability, or get_market_snapshot. Pagination guidance is present ("Pages default to 20 rows, maximum 100"), but there are no explicit exclusions or routing rules.
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.