bonhams_auction_detail

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

Annotations are absent, so the description carries the full burden and does add meaningful context: credential-free access, the data source (bonhams.com's own search API), and the historical/ended-auction coverage. However, it omits error behavior for invalid ids, the response structure beyond field names, and any rate-limit expectations — decent but not deep behavioral disclosure.

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?

Three sentences with action front-loaded first and supporting details following; the credential and historical-id context earns its place in the final sentence. The only real waste is redundancy — 'auction's normalized facts' appears twice in consecutive sentences.

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 single-parameter lookup with no output schema, the description compensates well by listing the returned fields and covering credential requirements and id scope. It doesn't describe the response container or invalid-id failure mode, but the sibling set (auction_lots, lot_detail, auction_search) completes the routing picture for an agent.

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% ('Bonhams auction id'), setting a baseline of 3. The description adds genuine value beyond the schema by clarifying the valid input domain: a historical/ended auction id resolves too, not just upcoming/live ones. For a single-parameter tool this fully explains the id's semantics.

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 and resource ('Get a Bonhams auction's normalized facts') and enumerates the returned fields (title, category, department, country, currency, sale dates, lot count). It distinguishes itself from siblings by calling out the search endpoint's upcoming/live-only scope, so an agent can tell it apart from bonhams_auction_search, bonhams_auction_lots, and bonhams_lot_detail without opening their schemas.

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?

Provides clear when-to-use context: pass an auction id when you need normalized facts, and it explicitly notes this tool resolves historical/ended auctions 'unlike the search endpoint.' It falls short of a 5 because it doesn't name the alternative tool explicitly or give a when-not-to-use exclusion (e.g., 'use the search tool to find an id first').

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