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

Annotations establish the safe read-only profile, but the description adds real behavioral context beyond them: the threadStatus distinction between 'stored' (full history cached) and 'preview-only' (latest message only), the fact that included threads are resolved server-side, and a footgun warning that threadUrl must not be used for sending (use conversationUrl instead).

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?

Three tight sentences, front-loaded with the core purpose, then row contents, then the read and reply workflows. Every sentence carries actionable information with no filler.

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 compensates by describing the row shape (participant, latest message, threadStatus) and the resolved thread attachment. Read-only annotations cover safety, and the reply handoff to send_unibox_reply closes the loop for the follow-on action.

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 genuine semantic value the schema lacks by pairing search + includeThreads as a workflow ('search by the lead name') rather than leaving includeThreads as an isolated flag. It also clarifies the non-parameter conversationUrl handle and its relationship to sending.

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 (merged LinkedIn Unibox conversations) scoped to the active setup, and immediately differentiates itself from alternatives by describing what each row contains. The agent can distinguish it from get_conversation, get_inmail_conversation, and get_inmail_inbox without opening a 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 explicit task-based routing: to READ a specific conversation, search by lead name and set includeThreads; to REPLY, pass the row's conversationUrl to send_unibox_reply. It even names the alternative tool and the condition that selects it, leaving nothing to inference.

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