Who you can ask

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

The readOnlyHint annotation already declares the operation is safe, and the description adds useful context about principals being otherwise unreachable and agents being cheap to interrupt. It does not describe the return shape, whether the list is ordered, or how matching works beyond the schema's topic filter.

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 compact sentences carry the entire definition with no filler. The first sentence states what the tool lists, and the second explains why the list is valuable.

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 a simple read-only filtered list, the description plus schema covers the core needs: what is listed, why it matters, and how to filter. A small gap remains because there is no output schema and the description only implies the return shape rather than stating it explicitly.

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 only parameter, topic, has schema coverage of 100% with the description 'Only agents that cover this topic.' The tool description adds no additional parameter-level meaning or examples, so it relies appropriately on the schema.

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 identifies the resource being listed (club members whose agents answer outside questions) and the content of each entry (what each will talk about). It does not explicitly contrast this with the sibling tools join and ask_agent, 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 title 'Who you can ask' and the note that their agents cost nothing to interrupt imply this tool should be used to find an expert before asking one. However, it never explicitly states when to use list_experts versus ask_agent or join, so the guidance remains implicit rather than direct.

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