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

Beyond the readOnly/openWorld/destructive annotations, it discloses non-obvious behavior: threadStatus values ('stored' = full history cached, 'preview-only' = only latest), that full history is resolved and attached server-side, and the critical conversationUrl-vs-threadUrl distinction for sending. This is exactly the kind of context annotations cannot 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?

Purpose is front-loaded after a compact Ids-in/out block, and each subsequent sentence carries distinct information (row contents, READ path, REPLY path). The bracketed header is slightly unusual but information-dense rather than wasteful.

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 supplies the return structure ('Ids out: inbox[].conversationUrl/readKey/participantProfileUrl') plus threadStatus semantics and the read/reply workflows. An agent has everything needed to call and consume the result.

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 the baseline is 3, but the description adds meaning: includeThreads is tied to a concrete workflow ('search by the lead name and set includeThreads') and search is scoped to a lead name. It clarifies intent beyond the schema's generic text.

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 gives a specific verb+resource ('Get merged LinkedIn Unibox conversations for the active setup') and immediately characterizes what each row carries (participant, latest message, threadStatus). This distinguishes it from siblings like list_chats and list_messages, which are attendee-chat and single-message oriented.

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 gives explicit routing for the two main follow-ups: READ via searching the lead name with includeThreads, and REPLY by passing conversationUrl to send_message. Strong alternative-naming, but it stops short of stating when this tool should NOT be used (e.g. versus list_messages or get_conversation).

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