get_model_guidance

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

Annotations indicate readOnly and idempotent, and the description aligns by discussing retrieval of guidance. It adds behavioral context by mentioning inclusion of learned overlays and research directives, which are not captured by annotations.

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?

Three sentences pack essential information without fluff. The first sentence front-loads the core purpose, followed by variant usage and research context, making it efficient and clear.

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?

The description covers return content, input usage, and connects to record_learning. The existing output schema compensates for missing return detail. A minor gap is the lack of explanation for default behavior when family/model_filename are empty.

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?

With 0% schema coverage, the description must compensate. It explains model_filename's role in variant overrides but does not elaborate on family values. This partial explanation provides some added meaning but lacks full clarity.

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 returns tuned settings for a model family, including sampling, resolutions, technique blocks, and prompt style notes. It distinguishes from siblings like list_models by specifying it provides configuration guidance rather than mere listing.

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 provides usage context like passing model_filename for variant overrides and advises verifying brand-new models online and using record_learning. While it doesn't explicitly exclude alternatives, it effectively guides when and how to use the tool.

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