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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds meaningful behavioral context: it mentions 'V2 pagination' and the available filters (type, before/after, archived, unread), and notes the LinkedIn exception. It does not contradict annotations and provides useful operational details beyond what annotations supply.

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 two sentences with no redundancy. The core purpose is front-loaded, followed by a compact list of capabilities and a crucial exception. Every word earns its place.

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 operation with 10 parameters and no output schema, the description covers the key aspects: provider scope, filters, pagination version, and the LinkedIn exclusion. The account_id parameter has its own schema description, so that is covered. It does not explain the return structure, but that is less critical for a list operation where the agent can infer a list of chats. Overall, it provides sufficient guidance for correct invocation.

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 only 10% (only account_id has a description), so the description must compensate. It explicitly lists the filter parameters (type, before/after, archived, unread) and mentions 'V2 pagination', which gives semantic meaning to cursor/limit/offset. However, it does not elaborate on the pagination parameters individually or explain the difference between cursor and offset, leaving some nuance unaddressed.

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 states a specific verb ('List') and resource ('chats') with an explicit provider scope ('WhatsApp, Instagram or Telegram'). It also differentiates from LinkedIn by noting the alternative requirement, making it clear that this tool is not for LinkedIn. This distinguishes it from the many sibling chat 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 a clear 'when not to use' by stating LinkedIn requires inbox-specific listing, which routes the agent to LinkedIn-specific tools like linkedin_list_inbox_chats. It also implies when to use it (for the three named providers), but it does not explicitly compare to provider-specific list tools like whatsapp_list_conversations or instagram_list_conversations, leaving some ambiguity about which to prefer.

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