Reset — reap this session's engine instances

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

No annotations exist, so the description carries the full burden. It explicitly states what gets killed, what is left alone ('Engines belonging to another running editor window are left alone'), and the effect and risk of all:true. This is thorough behavioral disclosure for a destructive tool.

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 dense sentences with no filler, front-loaded with the primary action. Every sentence adds essential information about scope, exclusions, and parameter usage.

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 tool is simple (1 param, no output schema), and the description thoroughly explains scope, behavior, and the optional parameter. The only minor gap is not describing return values, but for a cleanup operation this is acceptable.

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 the 'all' parameter (100% coverage), and the description reinforces its meaning and adds a safety condition. Baseline 3 applies, but the extra guidance justifies a 4.

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 'Kill every instance this session launched, and reap engines ORPHANED by earlier sessions,' which specifies the verb (kill/reap) and resource (engine instances). It clearly distinguishes itself from sibling kill_instance by focusing on session-level cleanup and orphan reaping.

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 explains when to use the tool (to clean up session instances and orphaned engines squatting bridge ports) and provides caution for the 'all' parameter ('only do that if you know no other session is using this engine build'). No explicit alternative tool is named, but the scope is clear enough to infer.

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