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

The description says 'Returns a NEW model id (ids are content addresses, so the original stays reachable)', implying a non-destructive operation. However, the annotations declare destructiveHint: true, directly contradicting that statement. This is a serious inconsistency for an agent deciding whether the call might destroy data.

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 dense but front-loaded: the core purpose and return value come first, followed by behavioral notes and a pointer to documentation. Every sentence contributes information; there is no filler, though the length is at the upper edge for a tool of this complexity.

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?

Given 5 parameters, no output schema, and the provided annotations, the description covers the main behaviors (new id, diff, asymmetry of levers, signature handling). It omits explicit error conditions or prerequisites, but it is largely sufficient. The destructive contradiction slightly reduces completeness because the agent cannot trust the safety profile.

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?

The schema already covers all 5 parameters (100% coverage), so the baseline is 3. The description adds meaningful detail: for 'tags' it clarifies that only refine.-prefixed keys refine and that both places and transitions work; for 'signature' it states that unverifiable signatures are refused rather than stored. These enrich the schema without being redundant.

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 specific verb ('Refine'), a clear resource ('a model's parameter classes'), and the mechanism (editing tags or assertedClasses), then says it re-derives and returns a new model id plus a diff. It is unambiguous and distinct from siblings like sim_classify or sim_calibrate, even without naming them.

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 explains the two levers ('tags can only split classes; assertedClasses declares a merge') and instructs the user to read sim://docs/classification for why they are asymmetric. This gives implicit guidance on when to use each, but it does not explicitly state when to prefer this tool over alternatives or when not to use it.

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