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

Annotations only declare readOnly=false, openWorld=true, idempotent=false, destructive=false. The description adds meaningful behavior beyond that: the call is asynchronous, returns an id and URL to poll, and an optional callbackUrl receives the answer. It doesn't state latency, whether questions can be withdrawn, or what the callback payload looks like.

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 tight sentences, front-loaded with the action and return behavior, then scope. The domain list is slightly long but earns its place by defining the expert's remit; no filler sentences.

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 an async, no-output-schema tool, the description covers the essentials: what happens on call, how to retrieve the answer, and the domain limits. It leaves the callback payload contract and the interaction with the get_answer sibling unstated, which is a minor gap.

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 low (17%) across 6 params, so the description should compensate more than it does. It does explain callbackUrl's effect (receives the answer) and the polling model, and 'person' is documented in-schema, but tags, asker and context are left entirely to the schema with no added meaning.

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 ('Leave a question for a person') and describes the async result (id + URL to poll), which implicitly contrasts with the get_answer sibling. It does not explicitly name get_answer or list_people as alternatives, so it stops short of full sibling differentiation.

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 scope guidance for the target expert ('emotions, sensations, intuition... product strategy, Kubernetes') and an explicit exclusion ('Not legal, medical or financial advice'), which helps decide when to use it. However, it never states when to use ask_person versus get_answer or list_people, nor any prerequisite for asking.

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