LinkedIn Intelligence MCP Server

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

With no annotations provided, the description carries the full burden of behavioral disclosure and excels at this. It explicitly states the action is 'IRREVERSIBLE' with concrete consequences (person must re-request connection), discloses that it 'Uses unofficial API' (important for reliability expectations), and mentions what happens on success ('Returns success status'). This provides comprehensive behavioral context beyond what any structured fields would 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 description is perfectly structured and economical: a clear purpose statement, parameter documentation, return value mention, and critical warnings—all in four focused sentences. Every element serves a distinct purpose with zero redundancy. The warning section is appropriately emphasized with capitalization and formatting.

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?

For a destructive, single-parameter tool with no annotations but with an output schema, the description provides exactly what's needed: clear purpose, parameter meaning, behavioral warnings about irreversibility and API nature, and mention of return value. The output schema will handle return structure details, so the description appropriately focuses on the critical context without over-explaining.

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 for the single parameter, the description fully compensates by explaining that 'profile_id' represents the 'LinkedIn profile public ID of the connection to remove.' This adds crucial semantic meaning not present in the bare schema. The description doesn't provide format examples or validation rules, which prevents a perfect score, but it successfully clarifies what the parameter represents.

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 specific action ('Remove') and resource ('existing LinkedIn connection'), distinguishing it from all sibling tools which focus on analytics, content creation, or profile updates rather than connection management. It provides a complete verb+resource statement that leaves no ambiguity about the tool's function.

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?

The description provides clear context about when to use this tool (to remove a LinkedIn connection) and includes a strong warning about irreversibility, which serves as implicit guidance about when not to use it casually. However, it doesn't explicitly mention alternatives or compare with other connection-related tools (like 'send_connection_request'), which prevents a perfect score.

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