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

Beyond the readOnly/openWorld annotations it discloses a concrete quota ('counts against a daily allowance (100 a day)'), the returned fields (name, headline, profile URL), and a prompt-injection safety rule for user-authored text — exactly the extra context annotations cannot 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?

Three short sentences, front-loaded with purpose before the `of` variant, then return shape, then quota and safety caveat. No sentence is filler.

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?

With no output schema, the description still names the returned fields, discloses the rate limit, and points at `of` for scope — leaving nothing an agent needs to call this read tool correctly. Pagination is covered by the `cursor` schema entry.

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%, so `of`, `limit`, `cursor`, and `connectionId` are already fully documented. The description restates the `of` semantics (member id vs. company numeric id) without adding format details or defaults beyond the schema, so the baseline 3 applies.

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 ('List who follows you on LinkedIn') and explicitly covers the two modes — self vs. another member or company page via `of`. It is clearly distinguishable from nearby siblings like get_my_connections and list_received_invitations.

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?

Explains the selection condition for the `of` argument ('omit for your own followers'), which is the main branching decision. It does not name an alternative tool or state when not to use this (e.g., connections vs. followers), so it stops short of full 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.