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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, but the description adds business-level consequences the annotations cannot convey: no unit is held, no payment is taken, no personal details are accepted, and availability is not guaranteed by the link. It also discloses the human-in-the-loop flow, which materially affects how an agent should frame the result.

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?

Four short sentences with zero filler: purpose first, then the three negative guarantees, then where availability comes from, then the human action. Each sentence carries a distinct, decision-relevant fact and the most important scoping information is front-loaded.

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 two-parameter link builder with a full output schema and complete annotation coverage, nothing an agent needs is missing: what it produces, what it does not commit to, and who completes the action are all stated. The return value itself is covered by the output schema, so the description need not explain it.

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 parameters (enum-restricted unit, YYYY-MM-DD moveInDate) are already fully documented. The description adds only the qualifier 'published' for unit size and 'optional' for the date, which are useful but largely redundant with the enum and the schema's own descriptions. 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?

States a concrete verb and artifact ('builds a link to the SJ Storage rental page') plus exactly what is prefilled (published unit size, optional move-in date in the enquiry form). This is clearly distinct from sibling tools like check_availability or get_units_and_prices, which an agent can rule out without opening a 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?

The description establishes the context for use implicitly and well: it is a hand-off to a human who 'reviews and sends the enquiry', and 'availability is confirmed on the page or by the office' tells the agent this is not an availability check. However, it never explicitly names an alternative ('use check_availability first') or states a when-not condition, so routing is left partly to inference.

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