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

The annotations only say this is a non-read-only, open-world, non-idempotent, non-destructive write; the description adds the crucial behaviour that the save is asynchronous and double-opt-in — PropertyList emails a link and the home is only saved when the person opens it. It also discloses that an account is silently created or opened with no password, which is meaningful side-effect context an agent would not otherwise know. It stops short of covering what happens on repeat calls or to an existing account's other favourites.

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 confirmation flow is front-loaded right after the purpose statement, and the agent-facing instruction ('Tell them to check their email') is short and actionable. The closing sentence largely repeats required fields already in the schema, which is the only real waste.

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 write tool with an output schema available, the description covers the essential missing piece — that success is deferred until the recipient clicks the emailed link — which is exactly what an agent needs to set expectations. Gaps around repeat invocations and existing-account behaviour are minor given the output schema and annotations.

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 75%, so the schema already documents all four parameters including the listing reference example and the enum for language. The description only restates the two required inputs ('the listing reference and their email address') without adding format or constraint detail, so baseline 3 applies.

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 states a concrete verb and resource ('Save a listing to a person's favourites (saved homes) on PropertyList') and clarifies the domain term with a synonym. It does not explicitly contrast with siblings such as save_search, so an agent must rely on the names alone to distinguish, keeping it just short of a 5.

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 gives operational guidance ('Tell them to check their email. Give the listing reference and their email address') but never states when this tool is the right choice versus save_search or request_viewing, nor any exclusion conditions. Usage is implied by the verb rather than explained.

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