remove_model

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

Annotations already declare destructiveHint=true, readOnlyHint=false and non-idempotence, so the safety profile is covered. The description adds genuinely new behavioral context by disclosing what survives deletion (reused files, shared checkpoints), which is exactly the non-obvious fact an agent needs before invoking a destructive tool.

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?

A single front-loaded sentence with zero filler; the scope limitation is stated before any caveat. Nothing in it could be cut without losing meaning.

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?

Safety annotations, a 100%-covered schema and an output schema carry most of the load, and the description covers the preservation behavior. But for an irreversible destructive operation it omits both the rerouting to unregister_model and any caution about the confirm/plan flow or what deletion does to dependents.

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 both `slug` (catalog ID/filename/alias from list_models) and `confirm` (true executes, false returns the plan) are already fully documented. The description adds nothing about either parameter, so the baseline 3 applies.

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 verb ("Remove") and a scoped resource ("owned artifacts"), and adds a distinguishing qualifier that reused files and shared checkpoints survive. That partially separates it from siblings like unregister_model (catalog-only removal), but it never names that sibling, so an agent comparing the two must still infer the boundary.

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?

There is no explicit when-to-use guidance, no prerequisite, and no named alternative. The phrase "owned artifacts" implies a condition, but the agent is left to infer why it would pick remove_model over unregister_model — a directly adjacent sibling that removes a catalog entry rather than files.

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