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

Annotations already flag destructiveHint=true and readOnlyHint=false, so the mutating nature is established. The description adds useful context: it sends a message and creates a new chat, and it distinguishes one-to-one vs group behavior. It doesn't disclose what happens on failure, partial group creation, or whether sending is immediate, but annotations carry the core safety burden.

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 the core purpose and providers. Every sentence adds useful routing or usage information. It is slightly terse given the optional parameters and complexity, but nothing is padded or redundant.

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 tool with 7 parameters, no output schema, and nested attachment objects, the description covers the core start-chat flow and the critical string/array behavior, but leaves gaps. It does not explain return values, error behavior, or the meaning of specifics/name/attachments. The schema covers account_id and users_ids, but overall context is only moderately complete.

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 29%, so the description must compensate. It does explain the critical users_ids distinction: string for 1-to-1, array for group. However, it adds nothing for text, name, specifics, or attachments, leaving several parameters semantically opaque. The schema documents users_ids and account_id well, but the description only partially fills the overall gap.

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 operation: start a new WhatsApp, Instagram, or Telegram one-to-one/group chat by sending its first message. It distinguishes the tool from the broader messaging_send_message and provider-specific tools, and explicitly excludes LinkedIn. This is a specific verb + resource with scope.

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 gives clear when-to-use guidance: use for starting new chats and resolving users_ids first. It also names an exclusion ('LinkedIn requires the inbox-specific start tool'), which routes the agent away from a sibling. It could be stronger by explicitly naming the LinkedIn sibling or distinguishing from messaging_send_message for existing chats.

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