serial_connect

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

Annotations already declare readOnlyHint=false and destructiveHint=true, so the safety profile is covered; the description adds genuinely new context the annotations cannot carry — the environment-variable prerequisite, the mandatory confirm_vm string, and the side effect of appending to a local log file. The word "dedicated" hints at exclusive pipe ownership, which is the likely reason for the destructive hint, though it could state outright that an existing reader will be displaced and that no port or guest configuration is performed as a remedy.

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 dense sentences with zero filler, ordered so the action and its side effect come first and the prerequisites/exclusions come second. Every clause (ALLOW_DEBUGGER, confirm_vm, log append, no port/guest config) carries distinct 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?

An output schema exists, so return values need no explanation, and the description covers the action, the side effect, the auth gate, and scope limits for a 4-required-param tool. The remaining shortfall is operational: it omits the teardown path (serial_disconnect) and the consequences of a failed attach, which matter for a tool flagged destructive.

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 0% (bare titles only), so the description must compensate and only partly does: it maps vm_name to "Running VM", log_path to the ".log file", and calls out confirm_vm as a requirement. It leaves genuine ambiguity — if the pipe is fixed at COM1, what value does the required pipe_name accept, and what must confirm_vm contain (presumably the vm_name echoed back)? Those two required params remain unexplained anywhere.

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?

States a specific verb and resource: attach a dedicated reader to the existing COM1 named pipe of a Running VM and append output to a local .log file. This is far more concrete than the sibling names serial_read/serial_status imply, though it never explicitly says how it differs from serial_read or debug_serial_prepare, leaving that inference to the 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 front-loads a real gate ("Requires ALLOW_DEBUGGER and confirm_vm") and a scope exclusion ("does not configure the port or guest"), which tells the agent when this tool is applicable. However, it never names the obvious alternatives or counterpart — serial_disconnect to tear the reader down, or serial_read/serial_status if a full log capture is not needed — so the when-to-use-vs-alternatives guidance is only implied.

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