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

With readOnlyHint and idempotentHint true and destructiveHint false, the safety behavior is already declared in structured metadata. The description adds product-specific behavior: the listing spans Classic, Sales Navigator, and Recruiter and requires an appropriate primary inbox for premium products. Return-shape and pagination are not disclosed, but these omissions are less critical here.

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?

Two sentences: the first states the action and scope, the second gives the workflow and the premium caveat. No filler or repetition, and the key usage guidance is near the front.

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 one-optional-parameter, read-only tool without an output schema, the description covers the operation, product scope, and downstream workflow. The main residual gap is not spelling out what an inbox object looks like or how primary inbox is determined, but the schema's account guidance and the simple list semantics make the tool usable.

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?

The schema fully documents the only parameter, account_id, including when to omit it and how to disambiguate multiple accounts. The description contributes no parameter-specific semantics, but because schema coverage is 100% the description does not need to; baseline 3 is correct.

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 first sentence names a concrete action (List) and resource (LinkedIn messaging inboxes) and narrows it to Classic, Sales Navigator, and Recruiter. It also distinguishes the tool from nearby siblings by positioning it before listing inbox chats and starting premium conversations, which is a different step from linkedin_list_inbox_chats or conversation-starting 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?

It explicitly places the call in a workflow: use before listing inbox chats or starting Sales Navigator/Recruiter conversations, so an agent knows the temporal context. The premium-primary-inbox sentence is a concrete prerequisite, but the description does not explicitly state when not to use this tool or name alternative list tools, so it is one step below fully explicit.

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