Create stack

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

Annotations only mark it as a non-read-only, non-destructive write; the description adds the meaningful extras: it mutates server state ('Side effect: creates the stack on the server'), it is reversible-feeling cleanup rather than deletion, and the first id becomes the cover. It does not cover preconditions such as whether assets already in another stack get moved or what errors occur with fewer than two ids.

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?

Purpose, rationale, ordering rule, and side effect are front-loaded in the first two sentences, and nothing is repeated needlessly. The 'Returns:' line is partly redundant given an output schema exists, and the docstring-style 'Args:' block is slightly heavier than needed for one parameter.

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 one-parameter write tool with annotations and an output schema, the description covers what it does, the ordering semantics, and the state change, which is enough to call it correctly. It leaves open the edge case of assets already stacked and any permission requirements.

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 0% and the schema only says 'array of string', so the description carries the load: it states the minimum count ('at least two') and the ordering contract ('Order matters: the first is the cover'), which is the single most important non-obvious fact about this parameter.

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 ('Group near-identical assets ... into one stack') and immediately explains the observable outcome (library shows the stack as a single item fronted by its primary asset). The 'gentler cleanup than deleting' line separates it from delete_assets, and the stack-focused siblings (list_stacks, update_stack, delete_stack) are clearly not what this does.

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?

Gives concrete use cases ('a burst, retries of the same shot') and an explicit alternative framing versus deletion, so an agent knows this is the non-destructive consolidation path. It stops short of naming other siblings it might be confused with, such as resolve_duplicates or update_stack.

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