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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds the meaningful caveat that the directory is opt-in only, which warns the agent that absence of an agent is not evidence it doesn't exist. It says nothing about pagination, ordering, or result size, though with zero parameters and no output schema those gaps are minor.

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, zero filler, with the scope constraint (opt-in) front-loaded and the next-step pointer trailing. Every clause carries information.

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 zero-parameter, annotation-covered read with no output schema, the description supplies the return-field list, the opt-in scope limitation, and the follow-up action. Nothing an agent needs to call or interpret it correctly is missing.

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 tool takes no parameters, so there is nothing for the description to disambiguate; baseline is 4. The field enumeration adds useful context about what the (parameterless) call yields.

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 identifies the resource precisely (agents that opted in to be listed) and enumerates the returned fields (name, description, card URL, skills, message acceptance), so an agent knows exactly what comes back. The verb is only implied ('Registered agents that...'), and it doesn't contrast with register_agent beyond the relay_message pointer, but the intent is unambiguous.

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 single pointer 'Message one with relay_message' tells the agent what to do next after listing, which is a useful routing hint. However, it never states when listing is appropriate versus register_agent (registering oneself) or get_inbox, so usage is only implied by the discovery context.

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