tandem_wait

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

With no annotations provided, the description carries the full burden of behavioral disclosure, and it does well. It explicitly states that the tool does not acknowledge terminal events, does not rerun work, and should only await events with a live independent watchdogikuha. It also explains that it returns ready IDs/questions, not full answers, which is critical for correct agent behavior. The only minor gap is not detailing side effects on the wait set state beyond removal, but the key behaviors are transparent.

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 succinct and well-structured. The core purpose is front-loaded in the first sentence, and subsequent statements efficiently cover key behavior without redundancy. Every sentence adds value, and the language is direct and actionable.

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?

Given the tool's moderate complexity (2 parameters, no nested objects, but with an output schema), the description is largely complete. It covers the behavioral nuances, references the output schema for return values, and provides clear usage guidance. It could be improved by explicitly clarifying the param semantics as noted, but the description is sufficient for an agent to call the tool 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 description coverage is 0%, meaning the schema's parameter descriptions are empty, so the description must compensate. The description mentions 'task_ids' implicitly through 'selected task' and 'ready IDs', and 'wait_seconds' through the time constraint ('not 25s per task'). However, it doesn't explicitly explain the meaning of task_ids (e.g., what format they should be in) or wait_seconds (e.g., the 25-second max and default 20). For a tool with 2 parameters, the description adds some meaning but not enough to fully compensate for the 0% coverage.

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 clearly states the tool waits for any selected task to finish or ask a question, with a specific verb ('wait'), resource ('selected task'), and scope ('ANY...not 25s per task'). It distinguishes itself from sibling tools by positioning the wait behavior and clarifying that it does not return full answers or acknowledge terminal events, which is unique among the siblings.

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 provides clear guidance on when to use this tool: to wait for tasks or questions, and instructs to use tandem_result for reading terminal results, tandem_reply for questions, and to remove resolved tasks from later wait sets. However, it doesn't explicitly state when not to use this tool or name alternative siblings for different wait scenarios, so it just misses a 5.

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