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

Annotations only signal mutating and destructive behavior; the description adds concrete risk context: daily connection_request budget, weekly cap, business hours gates, and a bypass that disables all safety checks. It even warns that LinkedIn may flag or restrict the account, which is material behavioral context beyond destructiveHint. No contradiction with 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 long but dense, front-loaded with the core action and then organized by platform, target, note, account, budget, and warning. The warning is slightly redundant ('bypasses ALL safety limits' vs. 'disables all protections'), but the repetition is defensible for a risky action.

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 no output schema and no parameter schema, this description covers every decision an agent needs: which platform, how to identify the target, note length, account selection, applicable limits, and the risk of bypassing them. It also routes to the correct sibling for other networks, making it complete relative to the available structured metadata.

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?

Because the input schema is empty, the description is the sole parameter documentation and it compensates well: it defines platform as required, target as profileUrl or leadId, note as max 300 chars, and accountId as conditionally required. The bypass flag is only described as 'When true' without an exact field name, but the semantics are still clear enough for an agent to act on.

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 opens with a specific action and target: 'Send a connection request to a profile.' It immediately distinguishes LinkedIn connection requests from other networks by naming campaignstack_follow_profile as the alternative, so the agent can disambiguate among the large sibling set.

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 states that platform is required and that on non-LinkedIn networks the agent should use campaignstack_follow_profile instead. It also gives a conditional rule for account selection: use campaignstack_list_accounts when more than one LinkedIn account is connected. This is direct when/when-not guidance.

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