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

Beyond the readOnlyHint and idempotentHint annotations, the description discloses synchronous execution, forbids task support, and details response handling (never display raw JSON, use assistantSummary, mention IDs only when useful). It also reveals error behavior (INVALID_INPUT rather than empty result) and that the returned JSON is internal state, all adding significant transparency.

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 reasonably compact but includes a long block about response formatting that, while valuable, could be streamlined. It is front-loaded with the core purpose and classification, and each sentence carries information, though the assetId retrieval note feels tangential.

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 the complexity of 9 parameters and the existence of an output schema, the description explains the critical scoping requirement and error handling but omits parameter semantics for most filters and does not clarify what assets are relative to creatives or advertisers. The confusing assetId sentence further reduces completeness, though the output schema likely covers return values.

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 9 parameters and 0% schema coverage, the description must compensate, but it only explains advertiserId and creativeId as scopes and confusingly mentions assetId (not in the schema) for retrieval. Other parameters like limit, cursor, status, seatId, seatName, accountId, and campaignId are left undocumented, leaving the agent without essential guidance.

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 clearly states the tool lists assets and specifies that assets are scoped resources requiring advertiserId or creativeId. However, it does not explicitly distinguish 'assets' from sibling list tools like list_creatives or list_advertisers, and the mention of retrieving a single asset with assetId blurs the line with get_asset.

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 description provides context on when to use the tool: listing assets within a scope, and explains that missing scope leads to INVALID_INPUT. It does not explicitly name alternatives or say 'use get_asset for single asset retrieval,' though the scoping hints are helpful. The response formatting instructions ('Use assistantSummary first') are more about agent behavior than tool selection.

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