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

With no annotations, the description carries the full burden. It helpfully discloses the async batch nature and a concrete cost cadence of 25 credits per size, but says nothing about permissions, whether existing renditions are overwritten, or rate limits.

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?

A single dense paragraph, front-loaded with the core purpose, followed by the operations and a routing instruction. Every clause (cost, async, action names, capabilities pointer) contributes; no filler.

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?

Given a complex multi-action tool with a nested free-form params object and no output schema or annotations, the description covers purpose and defers parameter detail to adgpt_capabilities — a defensible pattern. It still omits return-shape expectations, pagination for batch status, and sibling disambiguation, so it is only minimally adequate.

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 50%, with a free-form `params` object and only the action enum documented. The description mitigates this by mapping each action name to a short gloss and explicitly directing the agent to adgpt_capabilities with the operationId, but it does not itself add per-parameter meaning.

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+resource ('subject-preserving platform-size renditions of your generated image ads') and enumerates the five operations it supports. An agent knows what the tool family does, though the multi-action shape blurs a single crisp purpose and none of the siblings are named for disambiguation.

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 action list implies when each operation applies (presets catalog, batch status, campaign renditions), which is partial usage guidance. However, it offers no explicit when-to-use/when-not-to-use versus siblings like adgpt_edit_creative or adgpt_single_asset, leaving the routing decision to inference.

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