Combine trained minds (alias of singularis_mind_combine_v2)

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

Annotations establish the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=true), and the description goes well beyond them: no retraining, no data leaving the machine, quarantine of poisoned/corrupted inputs, refusal of tampered shards, and a cost model ('one job, independent of how the minds were trained'). The 'no data leaves this machine' claim sits in slight tension with openWorldHint=true but is about data egress rather than external interaction, so it reads as added nuance rather than a contradiction.

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 purpose is front-loaded in the first clause, followed by tightly packed op semantics, inputs, return, and cost — no filler sentences. The dense op enumeration is information-rich but slightly list-like rather than structured.

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?

With an output schema present, describing the return ('merged digest and counts') is a bonus rather than a requirement, and the destructive/refusal behaviors plus cost model cover what a mutation tool needs. The only notable gap is the unexplained structure of the 'params' object, which an agent must guess.

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% and the schema exposes only 'op' plus an opaque free-form 'params' object, so the description carries the burden. It partially compensates by naming the valid ops and expected inputs (mind file paths, output path, ridge default 1e-8), but never explains how those inputs map into the 'params' object or its key names, leaving a real gap.

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?

'Combine trained minds (model files) into one by exact addition' gives a specific verb, resource, and mechanism, and the title identifies it as an alias of singularis_mind_combine_v2, distinguishing it from the compute-kernel siblings. However, the subsequent enumeration of seven distinct operations (merge, add, remove, merge_quarantine, export_shard, import_shard, merge_shards) blurs the single-tool identity somewhat.

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?

Per-operation behavior is sketched (quarantine excludes a poisoned input; shards are signed and tampered ones are refused), which implies when each op applies, but there is no explicit when-to-use-this-vs-alternatives guidance. The alias relationship with singularis_mind_combine_v2 is only in the title, not stated as a routing rule.

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