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

Even with readOnlyHint=true, the description discloses important behavioral nuances beyond the annotation: `alive` means 'called the mesh within ttl_seconds', not 'reachable now'; a silent agent remains listed until expiry; messages to such a peer are accepted and stored but never read. It also explains that reading the directory counts as activity. This is exactly the kind of non-obvious runtime behavior an agent needs to interpret results correctly.

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?

The description is long but every sentence earns its place: core purpose first, then returned fields, then usage guidance, then a critical caveat about `alive`. Nothing is filler, and the most decision-relevant information is front-loaded. The density is justified by the tool's conceptual complexity.

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?

The description covers what the tool does, what each returned field means, how to interpret staleness, when to call it, how to use its output, and the side effect of calling it. With an output schema present and only two optional self-describing parameters, no essential operational detail 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?

Although schema coverage is 100%, the description substantially enriches both parameters. It explains that passing `agent_id` renews the caller's presence and that omitting it means nobody is renewed, and it clarifies the semantics and default of `include_stale`. This goes beyond the schema descriptions and helps an agent decide whether or not to pass each parameter.

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 names a specific verb and resource: listing agents across all user's machines in the mesh. It enumerates the exact fields returned (machine, role, repo, capabilities, status, status_age_s, last_activity_at, expires_at), so an agent knows precisely what this tool produces. It also implicitly differentiates itself from messaging siblings by explaining it is the source for the `handle` used to address an agent.

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 explicit, concrete when-to-use guidance: check it before heavy work such as a release, refactor, or deploy; use `status` + `last_activity_at` to distinguish working peers from stuck ones; use it to get a peer's handle; and re-run it before concluding a peer is unresponsive because its entry may have expired. It also mentions the related action `agent_send` in the intended workflow.

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