Send Prepared LinkedIn Connection Invitation

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

Beyond the annotations, the description adds critical behavioral details: the postcondition verification ('Pending is verified success and Connect is verified LinkedIn failure'), the immutable nature of the draft ('exactly one immutable invitation draft'), the list of server verifications (preview, payload hash, draft expiry, idempotency key, target identity, Send control), and the uncertainty handling for unreadable/ambiguous profiles. These go far beyond the annotations' flags.

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 about six sentences, each earning its place: a danger warning, approval policy, core action with verification list, postcondition interpretation, and edge case. It is front-loaded with 'Account-changing action' to immediately signal caution, and the structure progresses logically from conditions to outcomes without redundancy.

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—6 required params, approval interplay, and a separate output schema—the description covers the essential decision-making aspects: when to invoke, what the server verifies, the immutable send behavior, and how to interpret success/failure postconditions. The output schema exists to handle return values, so the description appropriately focuses on invocation and execution semantics.

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 only 33%, but the description meaningfully explains the roles of key parameters by listing them as verification criteria: 'exact preview, payload hash, draft expiry, idempotency key, target identity, and actionable Send control.' This gives semantic context to action_id, payload_hash, idempotency_key, and approval_preview. However, context_id and request_id remain unaddressed, and the schema already describes action_id and payload_hash, so the added value is moderate.

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 action: 'Send exactly one immutable invitation draft after the server verifies...' This specifies the exact verb, resource, and the execution phase (as opposed to prepare). The title 'Send Prepared LinkedIn Connection Invitation' aligns, and the focus on 'execute tool' differentiates it from prepare and other invitation-related siblings.

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 explicitly conditions invocation on the configured approval policy ('Invoke only when the MCP client's configured approval policy authorizes this exact execute tool') and states that interactive confirmation is the safe default. It also implies the preceding prepare step ('after the server verifies the exact preview, payload hash...'), but does not name alternative tools or explicitly state when not to use it, leaving some room for improvement.

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