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

It discloses the output format (grid of real people with portrait and role), the interactive behavior (each is ready to be spoken as), and the follow-up action (user picks one, conversation continues in that voice). This goes well beyond the annotations, which only mark the operation as read-only and idempotent.

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?

Two sentences deliver the trigger condition, example usage, output shape, and interaction flow. The most important usage guidance is front-loaded, and every phrase earns its place with no filler.

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 compensates by explaining the return value and the follow-up interaction. All parameters are already documented in the schema, and the annotations cover the safety profile, so an agent has everything needed to select and invoke the tool correctly.

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 covers all three parameters with clear descriptions, so the baseline is 3. The description's examples ('stoicism', 'Nietzsche') loosely illustrate the query parameter but add no meaningful structural or semantic detail beyond what the schema already 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 clearly states the specific action (find someone to learn from) and the resource (real people), with concrete example queries. It distinguishes from siblings by emphasizing 'has not named one yet,' which separates it from tools that probably require a named person or debate setup.

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 gives an explicit trigger condition and examples, and the phrase 'has not named one yet' implies a when-not condition. However, it does not explicitly name the alternative sibling tool (e.g., speak_as_person) for cases where a person is already named, so it stops short of full routing guidance.

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