pipeline_task

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

With no annotations, the description carries the full burden. It usefully discloses that timeout is per-task and that depth tracks delegation depth (a recursion hint), but says nothing about failure propagation mid-chain, blocking behavior, permissions, or what happens when depth is exceeded.

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 one-line purpose before the Args/Returns blocks; each line is short and earns its place. The Returns line is somewhat redundant given an output schema exists, but the overall structure is clean.

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 multi-step orchestration tool, the definition covers inputs adequately but omits operational behavior an agent would need: error handling across the chain, whether execution is synchronous, and the recursive depth limit. The existing output schema offsets the need to describe return values.

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 does: it documents all five parameters, clarifies that assistant_ids is a JSON list in pipeline order and context is a JSON object (matching the string-typed schema fields), and explains timeout is per-task. It stops short of format examples or defaults for depth.

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 mechanism: 'Chain assistants where output from one becomes input to the next.' This implicitly distinguishes it from siblings like parallel_task and debate_task through the sequential hand-off wording, but it never names or contrasts those alternatives, leaving the agent to infer the boundary.

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 phrase 'output from one becomes input to the next' implies the chaining scenario, but there is no explicit when-to-use guidance, no conditions for choosing this over parallel_task, debate_task, or delegate_task, and no prerequisites or exclusions stated.

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