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

Beyond the readOnly/idempotent/non-destructive annotations, the description discloses an important limitation: live-saleroom lots can return null prices regardless of the query, and the default is timed online sales. This explains expected behavior in a way annotations cannot convey.

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 dense sentences: the first front-loads purpose and outputs, the second explains the critical default and limitation. Every clause adds information, with no vague 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?

For a read-only search tool with six fully described parameters and no output schema, the description covers what results contain, the scope, and the main null-price caveat. Nothing essential for correct invocation is missing.

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 schema already documents query, category, page, limit, and include_unpriced. The description adds meaningful context on top, particularly the rationale for the sale_type default and the price-withholding behavior for live sales, which goes beyond the enum text.

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 names a specific verb ('Search Sotheby's past-lot archive') and enumerates the returned data: price incl. premium, hammer bid, estimate range, sale name/date/location, and department. It also distinguishes scope from a single-lot tool by saying it covers every sale in the index, not one auction.

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 clear guidance on sale_type: timed is the default because Sotheby's publishes those results, while live sales are searchable but return null prices. It does not explicitly name the alternative sibling sothebys_lot_details or state when to prefer results search over it, so it stops short of a full when-to-use/when-not-to-use instruction.

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