pick_variation

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

Because there are no annotations, the description must carry the full behavioral burden, and it does disclose the important destructive case: keep_only=true deletes the other variants and keeps only the chosen layer. It does not state what happens when keep_only=false, whether the discarded variants can be restored with undo, or what the call returns, so a substantial part of the mutation behavior remains unexplained.

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 short sentences, and both are front-loaded: the selection behavior comes first, and the destructive behavior comes second. It wastes no words on restating the schema and uses none that do no work.

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?

The description is adequate for a 3-parameter tool with no annotations and no output schema, but it cannot be called complete: the meaning of 'group' is undefined, the behavior of keep_only=false is never described, and there is no information about side effects in the layer stack or about recoverability. An agent has to guess at too much before calling it safely.

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?

With 0% schema coverage, the description has to define the parameters, and it does add real meaning for two of the three: index is 1-based and matches the numbering on the sheet; keep_only=true means delete the other variants. The required 'group' parameter is never explained, such as what identifier to pass or what it points to, which leaves the critical required parameter ambiguous.

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 uses a concrete verb+resource pair: it selects or shows one variant, by index, from a variants group that generate_image produced. An agent can tell that this is not generate_image itself, but it never names a sibling it should be used instead of, so differentiation is contextual rather than explicit.

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 'of a generate_image variants group' implies the precondition: call it only after generate_image has produced a set of variants. It gives no explicit when-not guidance, no stated alternative to use if there is no variants group, and no mention of how index ties to the sheet other than in the parameter note.

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