recommend_gpu_for_model

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 and it says nothing beyond the one-line purpose. It does not state that this is a read-only/analysis operation, what the ranking output looks like (ordering, scoring, tie-breaking), or what happens if no GPUs were discovered. For a recommendation/ranking tool whose value hinges on how "fit" is computed, this is a meaningful gap.

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 well-formed sentence with the scope and ranking criterion front-loaded and no wasted words. It is efficient, but the brevity here reflects under-specification rather than disciplined editing.

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?

A ranking tool with five input parameters, no annotations, and no output schema demands more explanatory text than one sentence. An agent cannot tell how the four optional parameters affect the ranking or what form the ranked result takes, so the definition is not complete enough for reliable invocation.

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?

Five parameters with 0% schema description coverage, and the description explains none of them. The only hint is "for the given model," which loosely ties to model_size_b; architecture, quantization (default q4), context_length (default 8192) and parallel_requests (default 1) are entirely undocumented in both schema and description, even though quantization and parallelism materially change the fit estimate.

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?

"Rank all discovered GPUs by estimated fit for the given model" gives a specific verb (rank), resource (GPUs), scope (all discovered) and ranking criterion, which is clearly distinct from siblings like list_gpus or get_gpu_info. It stops short of naming the closest alternatives (estimate_model_fit, compare_gpus, find_available_gpu), so the boundary must be inferred from the names.

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?

"All discovered GPUs" implies this is a whole-inventory ranking rather than a per-GPU check, which weakly routes an agent away from list_gpus / estimate_model_fit. There is no explicit when-to-use, when-not-to-use, or named alternative guidance despite three siblings that plausibly overlap.

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