check_vram_fit

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden of explaining behavior. It is transparent about inputs and return values (weights + KV cache + overhead in GB, compatible cards/Macs), but does not disclose estimation caveats, approximation assumptions, or limitations of the fit calculation.

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 two sentences long and front-loads the core purpose. It wastes no words and efficiently covers what the tool does, what it takes in, and what it returns.

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 read-only calculator-style tool with no output schema and no annotations, the description is reasonably complete: it states inputs, the computation, and the output shape. It lacks only explicit usage conditions or caveats, which are also relevant in other dimensions.

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?

The schema already documents all three parameters with 100% coverage, so baseline is 3. The description does add useful context by linking params_b, quant_bits, and context_tokens to the returned weights and KV cache, but it does not add significant detail beyond the schema.

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 verb ('work out whether') and a clear resource ('an open-weights model fits on a given GPU'), and lists concrete inputs and outputs. It does not explicitly differentiate from sibling tools like estimate_llm_cost, though the focus on VRAM/GPU memory is fairly distinctive.

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 implies the tool is for GPU memory-fit checks, but it does not state when to use it over alternative tools or mention any exclusions. A clear context is present ('whether a model fits on a GPU'), but there is no guidance about alternatives or edge cases.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.