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

Annotations already mark the operation as read-only, idempotent, and non-destructive. The description adds valuable behavioral context: execution is synchronous, task support is forbidden, the response is internal state, a compact inventory is returned, and an empty result is authoritative. No contradiction with annotations.

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?

The description is somewhat bloated, with multiple sentences about response formatting and user interaction (e.g., 'Use assistantSummary first', 'Never display raw JSON') that go beyond tool invocation. The core purpose is front-loaded, but the length and repetition reduce conciseness.

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 list tool with 11 parameters, no schema descriptions, and an output schema, the description is thorough. It covers the primary use cases, return content (creative names, IDs, sizes, statuses), the meaning of empty vs non-empty rows, and contrasts with get_creative. An agent has enough context to select and invoke the tool correctly.

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 description coverage is 0%, so the description must compensate. It adds guidance for campaignId, campaignName, advertiserId, and advertiserName, and mentions central pagination. However, it does not explain limit, cursor, status, seatId, seatName, accountId, or creativeId, leaving some parameters semantically unexplained. Partial compensation only.

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 opens with 'List Studio creatives' and establishes the tool as the authoritative saved creative inventory. It clearly distinguishes from siblings like get_creative (which provides full internals) and explicitly instructs to call this tool directly rather than get_campaign first, making its purpose and scope unambiguous.

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?

Provides explicit when-to-use guidance: prefer campaignId for deterministic reads, pair campaignName with advertiserId or advertiserName, and call directly as the first and only inventory read. Also states when to use get_creative instead and warns not to call get_campaign first, giving clear boundaries against alternatives.

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