aiworkhub_manager_loop_send

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

No annotations exist, so the description carries the whole burden and does it well: call returns at once with state 'running', a concurrent call is queued with a position (max 8, in-memory only), unrunnable routes are refused immediately, and per-route no-op vs. re-open handoff semantics are stated. Attachment size/type limits and which backends accept images are also disclosed.

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?

Front-loads the essential fact (one background turn, returns immediately), then handles the queue edge case and parameter notes in order. It is dense but a bit long; parentheticals like 'a switch re-opens with a mechanical handoff' earn their place but could be tightened.

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 an async, 5-parameter write tool with an output schema present, the description covers timing, queueing, refusal, route binding, attachment constraints, and the polling path for results. Nothing an agent needs to invoke it correctly and follow up is missing.

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 description coverage is 0%, so the description must compensate, and it largely does: backend_id/model route-binding semantics (blank = policy default, same route = no-op, switch = handoff), reasoning as depth choice, and images shape/size/backend support. Gaps remain – 'text' is undocumented and 'reasoning' gives no allowed values.

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?

States a specific verb and resource – 'run one manager turn in the background' – and the 'MANAGER WRITE' tag plus async framing distinguishes it from the loop lifecycle siblings (loop_new/loop_start/loop_continue/loop_status). An agent knows exactly what this does without opening the schema.

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?

Explains the immediate-return behavior and defines what to do next: poll aiworkhub_manager_loop_status (send_queue) or aiworkhub_manager_loop_events for the outcome. It does not explicitly contrast with loop_continue or loop_start, leaving the agent to infer which entrypoint to use for the first vs. subsequent turns.

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