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

The description goes well past the annotations by disclosing return contents (a card with portrait, call/keep-talking buttons), an accompanying brief on speaking style, lifetime knowledge limits, and off-limits topics. It also discloses the durable side effect — 'Answer as them from then on, following the rules that come with the result' — which annotations do not convey. It's docked one point because it never says how the persona is exited or how the result's 'rules' are surfaced.

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 discriminating clause before the examples, and the post-call behavior comes last where it belongs. The four quoted scenarios are slightly redundant with each other but each illustrates a distinct phrasing pattern, so the length is largely earned.

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 no output schema, the description correctly takes on the burden of explaining what comes back (card, portrait, buttons, style/knowledge/limits brief) and the ongoing behavioral contract. The remaining gap is lifecycle: how long the impersonation lasts and how to stop it are unspecified.

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 100% and the single mind_id parameter already carries an example value ('marcus-aurelius') plus a fallback hint to find_someone_to_ask, so the schema does the work here. The description adds nothing about the identifier, which is an acceptable baseline for a one-parameter tool but not additive.

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 capability in the first clause: 'hear FROM one specific person rather than about them', which is a precise verb+resource distinction rather than a restatement of the name. The four quoted example utterances pin down exactly what request shape this serves, so an agent can recognize the intent without opening the schema.

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?

Usage context is spelled out with concrete triggering phrasings ('what would Marcus Aurelius say about burnout', 'answer as Carl Jung', 'I want to talk to Socrates'), so when-to-use is unambiguous. What's missing is an explicit pointer to the alternatives — call_person and debate_two_people are neighbors that also involve a named person, and the description never says which request selects them instead.

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