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

Goes well beyond the destructive/non-idempotent annotations by explaining the actual flow: add returns a sign-in link that the person must open themselves, nothing is linked until they sign in, and credentials must never be requested in chat. It also discloses that removal takes effect on the next call and that person must be supplied on every subsequent call in the conversation.

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?

Dense but front-loaded, with the trigger condition first and the per-action behavior following. The parenthetical asides and long clauses make it slightly run-on, but nearly every sentence carries operational information an agent needs.

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 tells the agent what listing returns (linked people by first name) and what add returns (a sign-in link to hand over). Combined with the cross-cutting instruction to pass person on every tool call, an agent has everything needed to use this correctly.

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 coverage is 100%, so the baseline is 3, but the description adds real meaning: it explains the default (list) when no arguments are given, the pairing of action:'add' with first_name, and that person here only confirms while remove unlinks. The project parameter is left unexplained, which is the only gap.

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 resource and capability: linking multiple people who share the assistant to their own Connections accounts and acting as one of them. It is clearly distinguishable from connections_switch_workspace and connections_copy_connection, which concern workspace scope and connection duplication, not people.

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?

Opens with an explicit trigger ('Use when more than one person shares this assistant and each wants their OWN Connections account') and then gives the condition for each action: list for enumeration, add for inviting someone, remove for unlinking, and person for acting as them. Exclusions are also implied by the 'calls without it run as the connection's holder' clarification.

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