Disconnect

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

Annotations already indicate destructive, non-read-only, and idempotent behavior. The description adds nuance by explaining exactly what gets killed and under what conditions (launch vs attach, terminate flag), going beyond the raw annotations without contradicting them.

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 concise sentences with the primary action ('Close one session, or all sessions if all=true') front-loaded, followed by the key behavioral nuance. No redundant phrasing.

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 description covers all critical aspects: single vs all sessions, default termination behavior, and the terminate flag. The sessionId requirement is already in the schema. Adequate for a 3-parameter tool with no output schema.

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 coverage is 100%, so parameters are already documented. The description adds value by explaining the default for terminate (true for launch, false for attach) and clarifying the all flag, which enriches understanding beyond the schema's descriptions.

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 clearly states the tool's function: 'Close one session, or all sessions if all=true.' It also distinguishes behavior for launched vs attached processes, which differentiates it from sibling debug tools that pause, step, or continue.

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 provides context on default behavior (kills launched processes, leaves attached running unless terminate=true), which guides when to use it. However, it does not explicitly name alternative tools or state when NOT to use it, though the context makes the purpose evident.

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