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

With no annotations, the description carries the full burden and does: link lifetime of seven days, single use, never displayed in the response, re-invocation invalidates the previous link, and multiple refusal conditions. This is exactly the behavioral context an agent needs before calling a side-effecting tool.

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 critical facts (what it does, link lifetime, send_to meaning) are front-loaded, but the prose is dense and uses oblique metaphors — 'held at the shop', 'the box of whoever sets up the team's access' — where plain terms would be clearer. It runs long for the amount of structure it provides.

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 5-parameter, no-annotation, no-output-schema mutation tool, the description covers prerequisites, refusal cases, plan and role limits, re-invite semantics, and what the caller will and will not see. Nothing an agent needs to call it safely is absent.

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 earns more: it explains that send_to must be an address the person already reads or the access-setter's box, and that 'name' is for somebody new. The platform-mailbox acceptance rule for send_to is genuine added meaning beyond the schema.

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 makes clear that this tool invites a person to the account and creates passwordless access, so the verb and resource are identifiable. However, it never names its near siblings (add_team_member, add_queue_operator, add_mailbox_holder), so an agent must infer that this is the 'new person login' route rather than the existing-member route.

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?

Exclusions are unusually explicit: refused for someone who already chose a password, refused for a platform mailbox nobody signs in to, refused for support queues, only on accounts not held at the shop, never above manager. What is missing is positive routing — the description never says 'use add_team_member instead when the person already exists', leaving alternative selection to inference.

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