local_gpu_recommend_models

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

No annotations are provided, so the description carries the full burden. It does disclose key behaviors: it recommends one confirmed route plus alternatives, requires exact catalog IDs, displays the selected route and start_run_boundary, and defers execution until user confirmation. However, it leaves open what 'confirmed-capability' means, whether any state is mutated, and what happens on failure or multiple matches.

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, starts with the primary action, and includes critical constraints without any fluff. Every clause adds useful information, and the structure is easy 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?

Despite having an output schema, the description is incomplete for a tool with 11 parameters, 9 of which are required, and no annotations. It introduces undefined terms like 'start_run_boundary' and 'confirmed-capability route' without explaining them, and it gives no guidance on how to fill the required parameters or what the recommendation workflow should look like beyond the confirmation step.

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 input schema has 11 parameters with 0% description coverage, so the description must compensate. It only adds meaning for preferred_model_id ('must be an exact catalog ID'), while the other 10 parameters, including required ones like operation, profile, width, height, and authorization_scope, remain unexplained by the description. This is insufficient for a tool with many required parameters.

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 clearly states the tool's purpose: recommend one exact confirmed-capability route with up to two alternatives. It uses an action verb ('recommend') and references the resource (model routes), and it distinguishes itself from sibling local_gpu_start_run by explicitly saying it waits for later confirmation.

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 gives clear context for when to use this tool: before starting a run, and it explicitly says to wait for user confirmation before calling local_gpu_start_run. However, it does not mention when to prefer sibling tools like local_gpu_discover_models or local_gpu_inspect_workflow, so it lacks full alternative differentiation.

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