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

Annotations already declare readOnlyHint and idempotentHint, so safety is covered. The description does add real behavior beyond them: a 24s wait with a 45s ceiling, page sizes per delivery mode, and the instruction to follow nextAction silently. It omits what happens on timeout or on failure, which for a polling tool is material.

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?

It is short and front-loads the timing constraint, so nothing is padded. However, the telegraphic fragments ('Present; follow nextAction silently') are cryptic rather than efficient, trading clarity for brevity.

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?

With six optional parameters, no output schema, and minimal annotations, the description should carry much more: what is returned, how paging resumes, and what the other identifiers are for. It covers only timing and page capacity, leaving most of the calling contract unstated.

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 only 17% (just cursor), so the description must compensate. It partially does: 'native 6 previews, links 32 originals' gives meaning to the deliveryMode enum, 'max 45' bounds timeoutSeconds, and 'follow nextAction' explains cursor usage. batchId, taskIds, and requestId remain undocumented in both schema and description.

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 tells the agent it waits (24s, max 45) and paging capacities for native vs links, but never states that it returns images or how it relates to generation_status/generate_image. The verb 'wait' plus the tool name carries the purpose; the body text alone is a fragment, not a purpose statement.

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?

There is no when-to-use or when-not-to-use guidance, no mention of alternatives such as generation_status, and no statement of prerequisites (e.g., needing a batchId or taskIds). The only procedural hint is 'follow nextAction silently', which describes what to do after calling, not when to call.

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