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

Annotations already mark this as read-only and idempotent, so no safety contradiction exists. The description adds meaningful behavioral context: a 50-conversation cap, sort order by most recent activity, returned fields, and the conversationRef structure used by other inbox tools. It also discloses that the tool spans all LinkedIn accounts unless filtered.

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?

Four sentences, all dense and purposeful. The core action and scope appear first, followed by return details, identifier semantics, and filter/alternative guidance. No wasted words or redundant restatements of the schema.

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?

Given no output schema, the description thoroughly covers return shape, limits, sorting, filters, and related tools. The only notable gap is the unexplained workspaceId parameter, which prevents full contextual completeness for agents needing to target a specific workspace.

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?

With 0% schema description coverage, the description must compensate for parameter meaning. It explains unreadOnly and identityFilter well, even pointing to campaignstack_list_accounts for identity values. However, workspaceId is never described, leaving one of three parameters undocumented and forcing the agent to infer its purpose.

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 opens with a specific verb and resource: 'List inbox conversations across all LinkedIn accounts in the workspace.' It clearly distinguishes this from siblings like campaignstack_get_conversation and campaignstack_get_inbox_unread_count by focusing on listing conversation summaries rather than fetching message history or counts.

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 explicit usage guidance: use unreadOnly to filter unread threads, use identityFilter to restrict by LinkedIn account, and use campaignstack_get_conversation for full message history. This tells the agent when to use this tool versus a clear alternative.

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