Combine trained minds (v2: quarantine + shards)

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

Annotations already declare the mutation/idempotency/open-world profile, and the description adds genuinely useful context beyond them: no retraining and no data leaving the machine, quarantine exclusion of poisoned inputs, refusal of tampered shards, a returned digest/counts, and a cost model ('one job, independent of how the minds were trained'). This is meaningful behavioral disclosure for a mutating 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?

Front-loaded with the core action, then operations, inputs, return values, and cost in a logical order. It is dense and somewhat run-on with parentheticals, but every sentence carries information and nothing is redundant.

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 complex mutating tool with an output schema (so return values need not be re-explained) the description is largely complete: operations, quarantine/tamper behavior, inputs, and cost are all covered. The remaining gap is the absence of any differentiation from the near-identical sibling and the loose mapping of inputs to the opaque 'params' object.

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 0% and the schema exposes only an untyped 'op' string plus an unconstrained 'params' object, so the description carries the burden. It compensates well by enumerating the valid op values (merge, add, remove, merge_quarantine, export_shard, import_shard, merge_shards) and naming the expected inputs (mind file paths, output path, ridge default 1e-8), though it does not map these cleanly onto the 'params' object.

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 and resource ('Combine trained minds (model files) into one by exact addition') and enumerates the supported operations, so the agent knows exactly what it does. However, it never distinguishes itself from the sibling singularis_mind_merge_v2, which sounds near-identical, leaving the agent to guess which one to call.

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 implies usage through operation names (merge, add, remove, merge_quarantine, export_shard, etc.) and gives conditional behavior, but never states when to prefer this tool over singularis_mind_merge_v2 or the other compute siblings. There is no explicit when/when-not guidance or prerequisite information.

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