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

Annotations already declare this is a non-readOnly, non-destructive, idempotent, closed-world write. The description adds context annotations can't carry: authentication is required, and a side effect occurs (a first list is created if none exists, and an unknown `list` name silently creates a new list). It doesn't describe the response payload, but that gap is modest.

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?

Two tightly written sentences; the core action and destination come first, followed by the parameter branching and the auth requirement. No 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 should carry the return/confirmation story, and it does not say what a successful save returns or reports. Otherwise it covers the mutation semantics, side effects, and auth, which is nearly everything an agent needs 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 coverage is 100% so the baseline is 3, but the description goes further by defining the fallback semantics of `list` when omitted and the create-on-unknown behavior, which the schema's 'A shortlist name. Optional.' does not convey. It also implicitly documents that `id` comes from search_listings, matching 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?

States a specific verb (save) and resource (a listing) plus the destination concept (the person's shortlists, tied to the evryroom.com heart behavior), which cleanly separates it from remove_saved_listing and my_saved_listings. An agent knows exactly what this does without opening the schema.

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?

Explains the branching conditions for the optional `list` parameter (absent -> first list, made if none; unknown name -> new list) and the sign-in prerequisite, which is solid context. It stops short of naming alternatives or stating when-not-to-use (e.g., when the listing is already saved, or versus save_search).

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