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

Annotations already declare destructiveHint=true, idempotentHint=false and readOnlyHint=false, so the safety profile is covered. The description still adds useful context beyond annotations: that the user's network is mutated and that explicit user intent is required before calling.

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?

Three short sentences, front-loaded with the action, then precondition, then risk. No padding or redundant restatement of the tool name.

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 two-parameter tool with full schema coverage and annotations carrying the safety profile, the description covers purpose, prerequisite and caveat. It lacks detail on edge cases (target not currently connected, effect on pending invitations) and no output schema exists, but nothing essential to invocation is missing.

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 description coverage is 100% and the user_id description is exceptionally detailed (resolvers, forbidden inputs, format). The description only echoes the 'resolve the exact provider user_id' point, so it adds little beyond what the schema already provides — baseline 3.

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+resource: 'Remove an existing LinkedIn relation/connection.' It is separable from nearby siblings like linkedin_unfollow_user and linkedin_cancel_or_refuse_invitation by the word 'connection', though it never names those siblings explicitly to remove ambiguity.

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?

Gives a clear precondition ('Resolve the exact provider user_id first') and a caution about when this is appropriate ('changes the user's network and requires explicit intent'). It stops short of explicitly contrasting with cancel/refuse invitation or unfollow alternatives.

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