List GPUs

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety and open-world nature are covered. The description adds useful context that the result includes the automatically chosen device, but says nothing about ordering, stability, or what happens when no GPU is usable, which a discovery tool with no output schema would benefit from.

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 short sentence with no padding and the key qualifier ('babelscribe picks automatically') up front. It loses a point only because the sentence is an ungrammatical fragment that takes a second pass to parse.

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 no parameters and no output schema, the description should carry the full burden of describing what comes back. It hints at the content (list of GPUs plus the auto-selected one) but does not specify the return shape, device naming, or the empty/no-GPU case, leaving a real gap for a tool whose only purpose is discovery.

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 tool takes zero parameters, so the schema is trivially complete and there is nothing for the description to compensate for. Baseline 4 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?

The description names the resource (GPUs usable by whisper.cpp on this machine) and adds a distinguishing detail about automatic selection, but it is a noun-phrase fragment with no explicit verb and largely restates the title 'List GPUs'. An agent can infer it is a listing/discovery tool, but the purpose is implied rather than stated.

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?

There is no guidance on when to call this versus siblings like list_languages_and_models, nor any note on whether it should be checked before transcribe to confirm hardware support. Usage is left entirely to inference from the name.

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