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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=true, so the safety profile is covered. The description adds the key behavioral fact that this is a sticky default superseded only when an explicit model is given ("unless told otherwise"), which is real context beyond the annotations; it does not clarify that no image is generated by the call or what the response looks like.

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?

Two short sentences, with the effect of the call stated before the usage hint. Nothing is repeated and nothing is padding.

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 one-parameter configuration tool with annotations and no output schema, the description covers what it changes, at what scope, and when to call it. Minor gaps remain around invalid-model behavior and whether the change is user- or workspace-wide beyond the single mention of "this workspace".

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 coverage is 100% and the single parameter carries its own guidance ("A model from list_image_models"), so the baseline applies. The description adds only that the value becomes the workspace default, not any format, case, or error semantics for the argument.

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?

"Sets which model this workspace generates with" gives a specific verb (sets) plus the resource (generation model) and scopes it to the workspace as a persistent default. It is clearly distinguishable from list_image_models and generate_image, though it never names those siblings outright.

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?

"Use it when the user says they want a particular one from now on" is a concrete activation trigger that separates a persistent preference from a one-off generation. No explicit when-not or named alternative appears in the description; the pointer to list_image_models lives only in the schema.

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