Send a LinkedIn direct message

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

Beyond annotations (readOnlyHint false, destructiveHint true), the description discloses the two-call handshake, that confirm:true is required to actually send, that it counts against a daily messages cap, the dry-run behavior, and that InMail is never attempted. It also mentions the refusal condition. This is rich, actionable behavioral context that adds real value over the annotations.

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 dense yet efficient, front-loading the core action and then packing critical details (handshake, restrictions, dry-run) without fluff. Every sentence adds necessary information and the structure guides the reader through the flow logically.

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 the tool's complexity (two-call handshake, degree restrictions, dry-run mode), the description covers all essential aspects an agent needs to call it correctly: return of previewToken, refusal with not_connected, daily cap effect, and dry-run behavior. Without an output schema, it adequately explains the expected response shape.

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 carries the burden of explaining parameters. It explains profileUrlOrConversationId (URL/slug or thread ID), confirm (triggers the send in the second call), and previewToken (returned from the first call). It does not explicitly describe the text parameter, but its meaning is obvious as the message body. This nearly compensates for the lack of schema descriptions.

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 the tool's purpose: 'Sends one direct message' and specifies the two distinct target types (1st-degree connection via profile URL/slug, or an existing conversation via thread ID). This unambiguously distinguishes it from siblings like linkedin_create_post or linkedin_send_connection_request.

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?

Provides explicit usage conditions: only 1st-degree connections, refusal with not_connected, and the two-call handshake required for sending. It explains when the tool will refuse and how confirmation works, though it does not explicitly name an alternative tool for other messaging scenarios. Still, the context is strong enough for an agent to decide when to use it.

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