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

With all annotations false and no output schema, the description carries the disclosure burden. It does reveal meaningful process traits—an LLM call, a few seconds latency, auto-splitting of text—and the shape of the result. But it never states whether the built persona is persisted/overwritten or merely returned, which is a consequential side-effect ambiguity.

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?

Three sentences, front-loaded with purpose and free of filler. The scoping constraint and input guidance each earn their place.

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?

The description covers inputs, output composition, and latency, but with no output schema and uninformative annotations it omits whether the result is saved as a persona resource and how it relates to neuron_build_persona or neuron_build_persona_from_conversation. This is a meaningful completeness gap for safe invocation.

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 86%, so the baseline is 3. The description mostly repeats the text-vs.-vs.-samples distinction already in the schema and adds only marginal detail (example input formats). It does not explain speaker, platform, authorLabel, or description beyond what the schema provides.

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 opens with a specific verb and resource: 'Distill a reusable voice from raw text,' and names the output artifacts (voiceProfile components + exemplars). It also differentiates from sibling build tools by noting 'no Collection or browser extension needed' and by being explicitly text-input based.

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?

It clearly telegraphs when to use it: whenever the agent has raw pasted posts, transcripts, WhatsApp exports, or writing samples, and clarifies that no Collection/browser extension is required. However, it never names sibling alternatives such as neuron_build_persona_from_conversation or states when to prefer them, so it stops short of full when-not guidance.

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