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

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=true and non-idempotent, so the safety profile is covered. The description adds genuinely non-obvious behavior: intermediates are kept server-side and only the final step's value is returned, plus the dry_run verification path. It does not address the mild tension between readOnlyHint=true and the schema's note that dry_run checks "side effects", which an agent chaining write-like ops would want clarified.

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 core semantics (chaining, only final result returned) before the example. The inline JSON example is bulky but earns its place by illustrating the otherwise-abstract step format; nothing is redundant.

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?

An output schema exists, so return-value documentation is unnecessary, and the description covers execution model, result scoping, and a verification mode. The one gap is sibling disambiguation against run_recipe for a tool that otherwise reads as complete.

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 coverage is 100%, so the baseline is 3. The worked example goes beyond the schema by showing the exact step object shape and demonstrating implicit positional refs ("$page", "$1") in a realistic chain, which clarifies how steps compose.

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 concrete verb+resource: chaining operations into one call and returning only the final result. It is clearly distinct from discover/inspect/invoke, but it never distinguishes itself from the sibling run_recipe, which on its face sounds like a very similar batching tool.

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?

Offers one piece of real guidance ("Use dry_run=true first when unsure"), which is a useful precondition. However it gives no when-to-use versus run_recipe, invoke, or save_recipe, so an agent must guess which execution path to pick for a given task.

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