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

Annotations already declare destructiveHint=true and readOnlyHint=false, and the description adds substantial risk context: premium subscription requirements, daily budget limits, business hours gates, and a stark warning that bypass mode can disable protections and lead to account restriction. This goes well beyond the annotation basics and clearly discloses side effects.

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 longer than average but every sentence adds necessary guidance: prerequisites, target resolution, length limits, account disambiguation, budget gates, and a critical warning. The warning is placed at the end to avoid distracting from the main operation, and the high-value constraints are clearly ordered.

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 tool with an empty schema and no output schema, the description carries the full burden and covers nearly everything needed to invoke it: required platform, eligibility, target forms, content limits, account selection, and risk warnings. The main gap is the unnamed bypass parameter field and the lack of explicit parameter names/types that an agent would need to construct the call reliably.

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?

The input schema is empty, so the description is the only source of parameter meaning. It explains platform, target options (profileUrl or leadId), subject max 200 chars, messageText max 1900 chars, conditional accountId, and bypass behavior. However, the bypass instruction says 'When true' without naming the exact parameter, and no parameter names or types are formally structured, leaving a small but real ambiguity.

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: 'Send a LinkedIn InMail to a non-connected profile.' This clearly distinguishes it from sibling messaging tools like send_message, send_gmail, and send_connection_request by emphasizing 'LinkedIn' and 'non-connected profile.' The LinkedIn-only restriction is front-loaded.

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 clear context: requires Premium/Sales Navigator/Recruiter, targets must be non-connected, and account selection behavior when multiple LinkedIn accounts exist. It does not explicitly name alternative tools or state when NOT to use this tool, but the 'non-connected profile' qualifier strongly implies the boundary versus send_message or send_connection_request.

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