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

Annotations already declare readOnly/idempotent/non-destructive, so the description correctly spends its budget on pagination behavior instead: pages capped at 20, a page is not an exhaustive digest, and the cursor rule that the first page's size is retained while limit is ignored. That is real operational context beyond the annotations, though the tension between the 20-page cap and the schema's limit maximum of 250 is left unexplained.

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?

Six short sentences, no filler, and the core purpose plus the sibling preference lead the text. The pagination rules are dense but each sentence carries an actionable instruction; minor tightening is possible around the cursor/limit sentence.

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 7-parameter, no-output-schema tool with low schema coverage, the description adequately covers pagination and inbox selection but omits the semantics of the after/before time filters and is_unread, and never hints at the shape of returned chat records. Adequate but with visible gaps for an agent composing a filtered request.

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 carries a heavier burden, and it does clarify cursor semantics (limit ignored once a cursor is present) and that inbox_id must come from linkedin_list_inboxes. However, after, before, limit, and is_unread receive no explanation in either place, so the low-coverage gap is only partially closed.

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?

States a specific verb and resource ('List chats from a specific LinkedIn inbox') and explicitly positions itself against the generic chat listing and against sibling inbox tools by naming the LinkedIn V2 / Sales Navigator / Recruiter context. An agent can distinguish it from messaging_list_chats and linkedin_list_conversations without opening either schema.

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?

Gives an explicit preference rule ('Prefer this over generic chat listing for LinkedIn V2 and premium...'), a prerequisite ('Get inbox_id from linkedin_list_inboxes'), and a usage constraint ('list each intended inbox separately'), plus a pagination directive to follow every cursor. When-to-use, where-to-get-inputs, and how-to-iterate are all covered.

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