hardware_for_modelFor one model: how much memory it needs at each context length, the cheapest, best-value and fastest hardware that runs it fully in memory in a market, and their prices and speeds.
| Name | Required | Description | Default |
|---|---|---|---|
| model | Yes | A model slug, from search_models | |
| market | No | Where to price it: us, uk, de (Germany and the rest of the EU) or ca (Canada). | us |
| context | No | Context length in tokens: 8192, 32768, 65536 or 131072. |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, so safety is covered. The description adds genuine behavioral context beyond that: results are constrained to hardware that runs the model 'fully in memory', and the output bundles pricing and speed comparisons — a meaningful result-shape disclosure given there is no output schema.
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 with no filler and the subject ('For one model') front-loaded. It is dense to the point of needing a re-read, since three superlative tiers plus prices and speeds are packed into one clause, but nothing is wasted.
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?
With 3 parameters at full schema coverage and no output schema, the description does the important remaining work of describing the return payload and the 'fully in memory' filter. The one gap is the unresolved interaction between the enumerated context-length outputs and the single context parameter.
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 100%, so the baseline is 3. The description maps loosely onto the parameters ('in a market' → market, 'at each context length' → context), but 'at each context length' actually sits in tension with the single-value context enum and default of 32768, leaving ambiguity about whether all context lengths or just the selected one are returned.
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 names a specific resource (hardware for ONE model) and enumerates what is returned: memory required at each context length, plus the cheapest, best-value and fastest hardware with prices and speeds. That is far more specific than the title. It stops short of distinguishing itself from siblings like best_hardware, find_hardware or hardware_details, so an agent cannot fully rule those out from the description alone.
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 phrase 'For one model' implies a single-model scope, but there is no explicit when-to-use, when-not-to-use, or named alternative among best_hardware, compare_hardware, find_hardware and hardware_details. The only routing hint (obtain the slug from search_models) lives in the schema, not 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.