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

Annotations already cover read-only/idempotent/open-world, and the description adds a lot beyond them: sort order (cheapest first), what gets filtered out and that `criteria` reports what was read, omitted shipping where unpublished, the 0–1 match score with a below-0.2 heuristic, per-attribute verdicts with a three-state (true/false/absent) semantics, partial-failure reporting, and expected latency ("a few seconds").

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 operative content is front-loaded and dense, but the ~90-name seller enumeration consumes a large fraction of a single run-on paragraph and does nothing to help an agent select or call the tool. Most of the remaining sentences earn their place by substituting for a missing output schema; the list does not.

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?

With no output schema, the description carries the full burden and does: it enumerates returned fields per offer, explains match scores and verdicts, describes source success/failure reporting, both returned URLs, and rough latency. An agent could set expectations for and interpret the response without further documentation.

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 3 baseline is met by schema alone; the description still adds value about `query`'s compound grammar (price caps in the buyer's currency when unstated, attribute phrases like "wolf hall signed first edition under £200") and that `country` drives which sellers are searchable. The only gap is that country's ISO default is left to the schema.

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?

Opens with a specific verb+resource ("Search for a book") and immediately bounds the scope: every bookseller Near Fine covers for the buyer's country, including a concrete list of marketplaces and shops. Nothing in the sibling set (alerts, list_sources) does anything similar, so the routing decision is unambiguous.

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?

Gives concrete invocation guidance: pass an ISBN-10/ISBN-13 for an exact edition, or title and author keywords, optionally with a price cap or attributes. It also explains filtering behavior (over-cap and wrong-format offers are dropped). It stops short of explicit when-not-to-use or outlining follow-on steps like set_alert, though the alert mention hints at it.

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