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

Annotations already signal readOnly, idempotent, and non-destructive behavior. The description goes beyond this by explicitly stating which fields are returned (hammer price, premium-inclusive hammer price, estimate range, sale date, department), and by clarifying that the actual realized price is premium-inclusive, which is a useful behavioral nuance.

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 tight sentences capture the core behavior, the returned fields, and the optional filter. Everything is front-loaded and there is no repetition or fluff; each clause contributes essential context.

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?

There's no output, so the description's enumeration of return fields is essential and delivered. Pagination and radius are covered in the schema's parameters, while the description omits nonessential details like sorting behavior or result absence, making this sufficiently complete for a focused search tool.

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. The description adds meaning by clarifying the 'category' filter matches the department name and providing concrete examples (jewellery, prints), and by noting queries can be on artist, maker, or keyword. These details disambiguate free-text inputs better than the schema alone.

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 action ('Search') and a specific resource ('Bonhams' past-lot realized-price archive'), and it lists the returned fields. It does not explicitly name sibling alternatives like bonhams_lot_details, but the target use case is clear enough to distinguish it from a lot-detail lookup.

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 gives clear context for when to use the tool: when an agent needs archived realized prices and sale information from Bonhams. It does not provide exclusionary guidance or reference alternative tools, but the tool's name and purpose overlap sufficiently in a defined search scenario.

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