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

Annotations already mark destructiveHint=true, but the description adds important side-effect context: 'Marks FO rows parked — does not kill Terminal processes.' It also discloses dry-run behavior and the write-tier approval flow, going beyond what annotations alone provide.

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 dense and front-loaded with core semantics followed by parameter modes and caveats. The bracketed approval note is useful operational context, but it is somewhat long and includes agent-policy detail that could be trimmed without losing tool semantics.

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 a write operation with optional parameters and no output schema; the description covers use cases, parameter selection, side effects, exclusions, and approval requirements. It does not describe the exact output shape, especially for dry_run, but the behavior is clear enough for correct invocation.

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?

Even though schema coverage is 100%, the description enriches the parameters: stale_running=true is tied to 'running/unknown hosts that failed freshness (no recent heartbeat)', session_ids are tied to explicit targets from list/get tools, and dry_run=true is explained as 'previews only.' This is meaningful semantic guidance beyond the schema.

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 precise action and resource: 'Park THIS operator's coding host sessions' with N6 hygiene context. It distinguishes the tool from killing sessions ('does not kill Terminal processes') and connects it to list/clean-tabs workflows, so an agent can tell it apart from related session tools.

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 explicitly says when to use the tool: after 'clean tabs' / 'park ghosts' / when list shows dead running hosts. It also provides parameter-level decision rules (session_ids vs stale_running=true vs dry_run=true) and a clear exclusion: 'Never parks blocked_on_operator needs-you hosts unless listed in session_ids.'

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