get_model_guidance

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

Annotations cover safety (readOnly, idempotent, openWorld), but the description adds real conditional behavior: a learned overlay from past research may be merged in, a research directive may be present, and the `fit` block appears only when this GPU cannot hold the model. That conditional-output disclosure is exactly what an agent needs and is not derivable from structured fields.

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?

Front-loads what the tool returns, then moves to usage and conditional behaviors. Four sentences, all information-bearing; slightly dense but no filler.

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?

An output schema exists, so return values need not be restated, and the description covers the conditional blocks, overlay, and directive well. The remaining gap is the sibling-relationship and `family` parameter semantics, which matter for correct invocation.

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 0%, so the description carries the burden. It explains model_filename's behavior (alone it detects the family and applies turbo/lightning/distill overrides) but says nothing about `family`, its relationship or precedence relative to model_filename, or accepted filename formats.

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 resource and enumerates its contents (sampling settings, native resolutions, technique blocks, prompt style notes), which tells an agent exactly what this returns versus generic siblings like get_node_info or list_models. It never names a sibling for contrast, so it falls short of the top band.

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?

Gives concrete invocation guidance — passing model_filename alone triggers family detection and variant overrides — and routes the agent to record_learning for brand-new models. No explicit 'do not use when' or alternative-tool comparison, so it stops short of 5.

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