dsh_followup

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

The annotations show the tool is not read-only and not idempotent, but the description adds important behavioral context: the write is never automatically retried, and an attempted session.selectModel may persist as the DSH global default even when selection fails. This goes beyond what the annotations say, though it does not cover all possible side effects like auth failures or destruction.

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 but well organized: core purpose first, followed by a guardrail about task IDs, then mode behavior, routing caveats, and retry semantics. Each sentence earns its place and there is minimal redundancy.

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 write tool with no output schema and 8 parameters, the description covers the essential behavior needed to select the tool and make a correct call, including the no-guess rule, mode semantics, routing side effects, and no automatic retry. It is not fully complete because some non-required paramters like expectedRevision and sinceCursor remain semantically under-specified and the description does not mention what the agent should expect in return.

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 description adds real semantics for mode and model routing: queue targets the next turn, steer targets the active turn's next step, and routing can be omitted to inherit the session route. However, schema description coverage is low at 38%, and parameters like sinceCursor and expectedRevision are not explained in the description, leaving gaps for an agent that needs to use them.

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 specific action: continue the same known BridgeTask and root DSH session rather than creating a new delegation for the same work. It also gives a clear decision rule about known vs unknown task IDs, which helps distinguish the tool from sibling tools like dsh_delegate and dsh_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?

The description explicitly says when to use the tool, when not to use it, and what to do instead: never guess an old task ID and start a fresh delegation if no matching task ID is known. It also clarifies the queue and steer modes and the consequences of selection failure, leaving little ambiguity about correct invocation.

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