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

Annotations only declare readOnlyHint=false and openWorldHint=true; the description adds the externally visible side effect (an email is sent), the one-time/link-shown-once semantics, how the caller later authenticates with the key, and a commercial consequence (8 percent margin on bookings made with a key). That is substantial behavior beyond the annotations.

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?

A single tight paragraph with the core action front-loaded, followed by the follow-up flow, prerequisites, cost implication, and safety constraint in descending priority. 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 conveys what happens after the call (email sent, key revealed once to the recipient, not returned here) and the downstream auth format. Minor gaps remain, such as rate limits or delivery failure behavior, but the agent has enough to invoke it 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 description coverage is 100%, so both 'email' and 'label' are already documented in the schema ('Where the link goes.', 'A name for the key'). The description only implicitly clarifies that email must be the address owner's, adding little beyond the schema; baseline 3 is appropriate.

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?

Opens with a concrete verb and effect: 'Sends an email with a one-time link to a free Quub API key.' The resource (API key) and mechanism (emailed one-time link) are unambiguous and cannot be confused with any sibling such as search_hotels or prebook.

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?

States the trigger condition explicitly: a key is needed for prebook, get_booking and cancel_booking and raises search limits, naming the exact sibling tools that depend on it. It also gives a consent constraint ('Only send it to an address the person gave you for this'), which functions as a when-not rule.

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