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

Annotations declare only readOnly/destructive/openWorld, yet the description discloses cache-first behavior, live-fetch latency (~20s), the exists:false and uncertain:true edge cases, a post-deletion/block fallback that returns a synced copy with liveStatus, and the meaning of source:"inbox-preview". It even carries a third-party-data prompt-injection warning — far beyond what the annotations convey.

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 content is dense but nearly every clause carries distinct operational information (caching, edge cases, InMail routing, safety). The leading bracketed Ids-in/Ids-out block is awkwardly placed and slightly redundant with the schema, and the purpose sentence is buried behind it rather than front-loaded.

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?

With no output schema, the description carries the full burden of describing returns and does so: isFromMe flags, ordering, exists:false/uncertain:true, liveStatus, and source provenance. An agent can interpret every meaningful response state without additional documentation.

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 coverage is 100%, so all three parameters (refresh, connectionId, conversationUrl) are already documented, including the 'preferred' profile-URL form that the description largely repeats. The description adds no new syntax or constraints beyond the schema, so the baseline 3 is warranted.

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 — 'Read the message history of ONE LinkedIn conversation, oldest→newest' — with ordering and the isFromMe flag called out. The singular 'ONE' plus the conversationUrl-based addressing cleanly separates it from list_conversations, list_chat_messages and get_chat, and it flags that Sales Navigator conversations come back differently.

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 explicit operational context: when to pass refresh:true, which URL form to prefer, and how to act on the result ('reply to it with send_chat_message(chatId), not send_message'). It never states a when-not condition relative to the read siblings (get_chat, get_inmail_conversation, list_messages), so it stops short of full alternative routing.

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