mesh_serve

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It discloses that the tool starts its own serve-daemon on first use, that calls can be triggered repeatedly by any mesh caller, and that the command persists until mesh_unserve or process exit. It does not mention permission/trust requirements or failure modes, but the core behavioral risk is clearly disclosed.

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 compact, front-loads the core mechanism, and every sentence earns its place. The safety warning and pairing instruction are high-value additions, not filler.

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 no output schema and no annotations, the description covers the invocation model, persistence, and safety. It could add what happens on daemon startup failure or how errors are returned, but the essential context an agent needs to call it correctly and avoid misuse is present.

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 description coverage is 100%, so the schema already documents all four parameters. The description adds the stdin/stdout contract and the standing-surface semantics, which enrich the exec parameter's meaning, but it does not add detail beyond the schema for host, procedure, or exec_timeout_seconds. Baseline 3 is appropriate.

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 states a specific verb ('Advertise a procedure on the mesh'), the resource (a procedure answered by a local shell command), and the exact execution model (run once per inbound call, stdin/stdout contract). It clearly distinguishes this from one-shot mesh operations and from mesh_unserve, its natural sibling.

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 explicitly warns that this is a standing inbound surface, not a one-shot action, and tells the agent to pair with mesh_unserve to stop serving. It also gives a strong safety rule: never register a command a stranger could run repeatedly. This is explicit when-to-use and when-not-to-use guidance.

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