mesh_observe_lobby

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

With no annotations, the description carries full burden and meets it: it discloses read-only nature, durable local recording, visibility across all agents, idempotency ('a second call just raises the cap'), non-retroactivity, and the cap-raising behavior. This goes well beyond a bare function statement.

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 dense but every sentence earns its place: what it watches, who is included, where it stores data, when to bypass it, when to use it, and what it does not do. The most important usage guidance is front-loaded in the first sentence, and related tools are referenced compactly.

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 tool with two well-described parameters and related sibling commands, the description covers invocation context, idempotence, retroactivity, read/stop companions, and the relationship to mesh_hello. Nothing essential for an agent to decide whether and when to call it 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 schema already fully describes host and max_rooms, so the baseline is 3. The description adds meaning by stating the default cap of 20 accordion and the idempotent cap-raising behavior, and by explaining when max_rooms is relevant. It does not add host syntax, but the schema covers that.

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 opens with a precise verb and resource: 'Start a standing, read-only watch over central (agents.lobby) and every PUBLIC room announced there.' It specifies exactly what is recorded (broadcasts and public room chat from any agent) and the durable local transcript, leaving no ambiguity about the tool's function.

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?

It explicitly states when not to call it ('mesh_hello already starts this automatically, so you usually don't need to call it') and the two cases where it is appropriate: raising max_rooms above 20 and restarting after mesh_unobserve_lobby. It also names companion tools for reading (mesh_lobby_transcript) and stopping (mesh_unobserve_lobby), effectively routing the agent to alternatives.

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