probe_capabilities

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

With no annotations, the description carries full behavioral disclosure. It clearly says real API calls happen, a small amount of generation quota is consumed, only a small default set is probed, and results are written into a local cache. The schema note adds that video is submitted but not waited on, which is also useful behavioral context.

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 compact and front-loaded. It states the core behavior first, then covers cost/default scope, then cache merging, then the optional model argument. Every sentence contributes relevant operational information without repetition.

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 side-effectful probe tool with no output schema, the description is mostly complete: it explains cost, default behavior, caching, merging with `list_model_capabilities`, and the optional model filter. One minor gap is that it doesn't explicitly say what the probe call itself returns, relying on the cache-merge behavior to infer where results end up.

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%, so the schema already documents the `note` and `model` parameters well. The tool description adds the useful context that `model` optionally restricts probing to a specified model and defaults to all configured models, but it doesn't go beyond what the schema already suggests.

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 states a clear active purpose: it actually probes the current supported resolutions/aspect ratios for each model, which is distinct from simply listing them. It also differentiates from the sibling `list_model_capabilities` by explaining that probe results are merged into that list.

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 makes the usage context clear: use it when real probing is needed, consume a small amount of quota, default to a few combinations, and optionally restrict with `model`. It also implies the alternative—`list_model_capabilities` merges the probe results—but it does not explicitly state when to avoid this tool and use the list instead.

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