swg_withdraw

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

With only readOnlyHint=false from annotations, the description carries the burden and delivers: it states the effect (handoff ends, fence lifts), the two refusal errors and that they 'change nothing,' that next_step says to stop and report, and the SINGLE-HOST scope plus the out-of-guarantee caveats. This is exactly the mutation-consequence and failure-mode context annotations cannot 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 core purpose is front-loaded, which is good, but the prose is dense with internal jargon ('handed_off refusal', 'handoff_not_giver', 'fences the giver') and the trailing guarantee-disclaimer list reads as a dump. It is informative rather than concise, and parsing cost is high.

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 single-parameter mutation tool with no output schema and minimal annotations, the description covers purpose, effect, error behavior, scope limits, and untested cases. The main remaining gap is that parameter format and any return/next_step schema are left implicit, but overall it is complete enough to invoke correctly.

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 0% for the single 'path' parameter, so the description is the only source; it contextualizes the parameter as a path previously handed off by this session but gives no format or example. For a self-evident single path argument this is adequate but does not fully compensate for the coverage gap.

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 names a precise verb and resource: withdrawing 'this session's live handoff of a path,' with the concrete effect that the handoff ends and the fence lifts. It also implicitly contrasts with the sibling swg_transfer ('A transfer fences the giver and does not reserve the path'), so an agent can distinguish the two operations. It stops short of an explicit 'to hand off, use swg_transfer' routing statement.

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 gives an explicit precondition ('Take it only on the user's or host's explicit instruction') and a clear when-not ('It is never the recovery for the handed_off refusal'), directing the agent to stop and report instead. That is strong contextual guidance, though it never names a sibling tool as the alternative action.

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