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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, covering safety. The description adds valuable behavioral context: reading inboxes sequentially to respect rate limits, reporting unreadable inboxes as 'unavailable' instead of failing, and preserving inbox_id and chat.id. This goes beyond annotations and helps the agent understand expected behavior.

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 fluff. It front-loads the core purpose, then explains default behavior, extension options, rate-limit handling, and a specific usage instruction. Every sentence contributes meaning, making it highly efficient.

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 read-only list tool with no output schema, the description covers key operational aspects: default inbox, how to specify other inboxes, rate-limit behavior, error handling for unreadable inboxes, and a usage hint. However, it does not explain the output structure beyond mentioning preserving inbox_id and chat.id, nor clarify whether limit applies per inbox or total, and lacks pagination details. Given the tool's complexity, these are minor gaps.

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 67%. The description text reinforces the inbox_ids usage but does not add significant detail for limit or account_id beyond what the schema already provides. The account_id parameter has a detailed schema description, and the limit parameter lacks description in both places. The description adds minimal value for parameters beyond schema.

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 'List LinkedIn private conversations' with a specific verb and resource. It also explains the default inbox and how to access other inboxes, which adds specificity. However, it does not differentiate from the sibling tool 'linkedin_list_inbox_chats', which likely has a similar purpose, so the distinction is unclear.

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 guidance on when to use this tool: 'Use before linkedin_read_conversation when chat_id is unknown' and explains how to pass inbox_ids for other inboxes. It provides context on default behavior and how to extend it, but does not explicitly state when NOT to use it or mention alternatives like linkedin_list_inbox_chats.

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