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

With no annotations at all, the description carries the full burden and does so well: one-time use, 15-minute expiry, recipient must be a shop member resolved by membership_id, and the page re-checks access on open. This is exactly the security and lifecycle context an agent needs before sending a privileged link.

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?

Front-loaded with the core action, then the screen variants, then the security constraints. Dense parenthetical clauses for each screen earn their place, though the first sentence is long enough to require re-reading.

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?

Given four params, a nested params object, and an output schema, the description covers purpose, per-screen permission rules, expiry, and one-time semantics. It omits failure behavior (e.g. member not found) and any rate/send limits, which are the only meaningful gaps.

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 only 25%, but the description compensates for the two non-obvious params: it defines what each screen value opens and the preconditions attached (owner-only, field worker must be assigned to a visit), and explains that membership_id constrains delivery to the shop. shop_id is left undefined, though its meaning is self-evident.

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?

A specific verb and resource — email a one-time sign-in link to a current member — followed by the exact three destination pages this link can open. An agent can distinguish this from siblings like auth_sendLink or members_resendInvite because the description enumerates the screens and their access rules.

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?

The description gives clear selection logic for the screen parameter (board for owner/office, override owner-only, capture for anyone on the job with an assigned visit) plus the overall 'Owners and office only' gate. It stops short of naming a sibling alternative or saying when not to use this versus the other link-sending tools.

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