swg_transfer

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

With only readOnlyHint=false in annotations, the description carries the behavioral burden and does so: it discloses per-path success/failure answer shapes, typed refusal reasons (handoff_not_held, handoff_successor_unknown, handoff_in_flight), retryable=false and recover values, the fencing effect on swg_write/swg_write_cas during a live handoff, and the explicit non-guarantees (SINGLE-HOST only; cross-host, network mount, divergent history, auto-merge not detected in v1).

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 purpose is front-loaded correctly, and most clauses carry real routing or recovery value, but the body reads as a dense run-on that packs multiple obligations into single sentences. Splitting the error/recovery matrix into the same structured form as the answer list would make it scannable without losing content.

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?

Despite having no output schema, the description fully specifies the return contract (transferred=true/false, record fields, typed reasons, error-on-any-refusal, top-level aggregation) plus recovery and retry semantics and scope limits. An agent has everything needed to call it and to interpret every outcome.

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%, so the description must compensate. It precisely defines `successor` ('the session_agent_id that the successor's OWN swg_status reports') and describes `paths` behaviorally (one grant per path, answered in order). It does not specify path format (absolute vs relative vs glob), which is the remaining 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 first sentence names a precise verb and object ('hand this session's claim on one or more paths ... to another session, the successor') and immediately identifies what is being transferred (the write grant from swg_write or the standing read from swg_read). It is unmistakably distinct from siblings like swg_withdraw and swg_accept, and the direction of the transfer is explicit.

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 states when to use it, when NOT to re-use it ('do not transfer again, and do not withdraw to start over'), and how to disambiguate commit_unconfirmed by inspecting the path's handoff. It also names the specific conditions for retrying and the fallback ('ask your user'), and warns against writing a handed-off path by any route other than MCP.

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