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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the description's added value is the newest-first ordering, the exclusion of logos and Studio takes, and the pagination chaining via next_offset. That is meaningful behavioral context beyond structured fields, though it says nothing about result size or whether generations are filterable by project.

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, zero filler, with the primary purpose and scope front-loaded ahead of the minor pagination detail. Every clause carries information.

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 values need not be described, and pagination is already explained. For a simple read-only list tool, nothing an agent needs in order to call it correctly is missing.

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 all three parameters (including the kind enum and offset semantics) are already fully documented in the schema. The description restates the limit bounds and the next_offset chaining rather than adding new meaning, so the baseline 3 applies.

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 (List) and resource (the account's Create generations) with the ordering rule (newest first) and explicit scope exclusions (logos and Studio takes are not listed here). An agent can tell this apart from get_generation or list_projects without opening the schema.

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 exclusions carve out a clear scope boundary and implicitly tell the agent this is the enumeration entry point rather than a detail fetch. It does not explicitly name an alternative sibling (e.g. get_generation for a single item) or state when not to use it, so it stops short of a full when/when-not statement.

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