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

Annotations already establish readOnly, idempotent, and non-destructive behavior. The description adds valuable behavioral details: random sampling, publication status filtering, owner-claim prioritization, and deduplication via exclude. This goes beyond what annotations alone convey.

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 compact and front-loaded with a clear 'when to use' marker. Every sentence contributes: trigger phrases, sampling behavior, prioritization, comparison to search, and exclude usage. No filler or redundant content.

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 simple, zero-required-parameter random feed tool, the description covers the key aspects: when to invoke, what it returns conceptually, how results are prioritized, and how to paginate without duplicates. No output schema exists, but the resource being returned (products) is clear from the description.

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 100%, so the schema already documents both parameters. The description reiterates the exclude parameter's purpose for continuation requests but adds no new semantic information beyond the schema.

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 randomly samples published products, prioritizing products with claimed owners. It distinguishes itself from search by explicitly saying it fits the 'I don't know what I want' scenario, making its purpose and identity clear among sibling tools.

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 explicit trigger phrases ('随便看看', '让我发现些有意思的', '给我推荐点东西') and explains why random_feed is preferable to search in open-ended discovery scenarios. It also gives continuation guidance with exclude. However, it does not contrast against other discovery-style siblings like personalized_feed or list_products_discover.

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