emergency_stop

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

Goes well beyond the annotations by disclosing the physical consequences (everything stops, heaters off), the irreversible-ish follow-up state (board must be restarted), and the approval/auth behavior (always available, never asks for approval). Note a mild tension with destructiveHint=false, since this aborts an in-progress job and forces a restart, but the description does not literally contradict the hint.

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?

Three short sentences, front-loaded with what the tool does, followed by the consequence and the availability/approval caveat. Every sentence earns its place with no 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 parameterless emergency action with no output schema, the description supplies everything an agent needs: the trigger semantics, the effect, the recovery requirement, and the fact that it is always permitted. Nothing material 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 zero parameters, which is the baseline-4 case; the description correctly signals a no-argument action. No parameter semantics are needed or omitted.

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 action (emergency stop), maps it to the underlying G-code (M112), and enumerates the concrete effect: stops everything at once and switches heaters off. This is unmistakably distinct from the read-only status siblings like get_status, job_status, and get_sensors.

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?

Gives clear operational context: always available, never requires approval, and requires a board restart afterwards (power cycle or M999 with approval). It doesn't explicitly contrast itself with a graceful 'cancel job' alternative, but it does describe the recovery path and approval semantics, which is strong guidance for a last-resort action.

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