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

Annotations declare readOnlyHint=false, idempotentHint=false, destructiveHint=false, openWorldHint=true. The description doesn't contradict these but also adds nothing beyond them: it doesn't say whether unfollowing is reversible, whether it requires permission, or what happens if the user is not currently followed. With annotations carrying the safety profile, this is adequate but thin.

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?

Two short sentences, front-loaded with the action. No waste, though the second sentence merely restates what the schema already documents.

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 simple two-param mutation with full schema coverage and existing annotations, this is close to sufficient. The missing piece is the relationship between unfollow and remove_connection, and reversibility, which an agent would benefit from before invoking.

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 param description already explains obtaining it via resolvers and lists what never to pass. The description's only addition is a one-line reminder to resolve first, which is redundant with the schema. Baseline 3 is correct.

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 (Unfollow) and resource (LinkedIn user) from the connected account. A sibling tool linkedin_follow_user exists, and the name plus description make the direction of the relationship operation unambiguous.

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?

Adds a sequencing prerequisite ('Resolve the exact provider user_id first'), which is useful guidance. However, it never explicitly contrasts with alternatives like linkedin_remove_connection (removing a connection vs unfollowing) — a distinction an agent could easily get wrong given both exist as siblings.

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