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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds genuinely non-obvious behavior: results are ordered largest first, and each entry uses the most faithful weight format that still fits, which tells the agent how to interpret the returned weight field without a second call.

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 tight sentence with zero filler, and the sort order plus format-selection rule are front-loaded. It is arguably over-compressed — the sentence omits an explicit verb and reads as a fragment, which slightly reduces scannability.

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 seven parameters, no output schema, and no annotations covering returns, the description should say more about what each result contains (model entries, chosen format, fit margin?). It conveys ordering and format choice but not the shape or breadth of the response, nor whether the catalog is bounded.

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%, including defaults and enum meanings, so the schema carries the parameter burden. The description only indirectly gestures at two parameters ("GPU(s)" for gpu_count, "most faithful weight format that fits" for weights) and adds no new semantics. Baseline 3 applies.

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 outcome: it returns every listed open model that fits on the given GPU, sorted largest first. This clearly separates it from estimate_vram (single-model VRAM estimate) and gpu_prices (pricing), though the verb is implied rather than stated outright ("Every listed open model that fits...").

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 purpose implies when to use it — you have a GPU and want the set of viable models — but there is no explicit guidance such as "use estimate_vram instead when you already have a specific model in mind." No prerequisites, no exclusions, and the sibling tools are never referenced.

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