chain

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

Describes data flow (output as context) and that stages support sandbox fields, but lacks detail on error handling, resource usage, or execution semantics. With no annotations, more transparency would be beneficial.

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?

Two sentences for purpose and a clear explanation of stages format. No fluff, front-loaded, efficient.

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?

Covers input semantics and pipeline behavior adequately. Missing edge cases but output schema exists, so return values not needed. Good for a simple tool.

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 only parameter 'stages' is a string, but description clarifies it is a JSON array of stage objects and lists supported sandbox fields, adding significant meaning beyond the schema.

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?

Description clearly states the tool runs agents sequentially as a pipeline, and explains that each stage receives prior output as context. This distinguishes it from sibling tools like 'par' (parallel) and 'map_reduce'.

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?

Implied usage for sequential processing, but no explicit guidance on when to use vs alternatives or when not to use. Could mention that 'par' is for parallel execution.

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