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

Annotations already flag destructive=true and non-idempotent behavior. The description adds useful context beyond those annotations: rotate replaces the link and the old link stops working, and omitting rowId yields each home's link. Permissions and exact return behavior remain unstated.

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 description is short, but the fragmented phrasing 'No rowId: each home's link. rowId: make it' is hard to parse and is not front-loaded with a clear verb. Every word is doing something, but the structure could be much clearer.

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 four parameters, no output schema, and a destructive rotate option, the description should clarify what is returned (a single link vs. per-home links) and what id and slug identify. It covers the rotate consequence but is too cryptic for complete invocation confidence.

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 50%: id and slug have only terse schema descriptions, while rowId and rotate are undocumented in the schema. The description compensates by explaining rowId omission vs. presence and rotate replacement, but id and slug semantics remain thin.

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 explains that the link is for Airbnb, Vrbo, or Booking.com to import availability, so the resource is identifiable. However, it never clearly states the action (return vs. create) and does not distinguish itself from siblings like get_calendar or remove_calendar_link.

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?

It describes conditional behavior for rowId and rotate but gives no explicit guidance on when to call this tool versus alternatives such as get_calendar or remove_calendar_link. The agent must infer the use case from the name and cryptic notes.

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