market_stats

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

Annotations already declare readOnlyHint=true and openWorldHint=true, and the description adds meaningful context beyond that: stats are computed server-side over the full matching set rather than a sample, and sold_only=true restricts to sold lots with a positive USD price so results reflect realized transactions. No auth, rate-limit, or cost disclosure, but the sampling and sold-only semantics are genuinely useful behavioral details.

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 purpose and return set are front-loaded, followed by per-argument notes, so the structure is easy to scan. The Args-style block is slightly verbose and the return enumeration is somewhat redundant given an output schema, but nothing is outright 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 3-parameter read-only aggregation with an output schema, the description covers the argument semantics and the key caveat about full-set versus sampled computation. The remaining gap is relational: it never positions itself against market_index or price_trend, so an agent must guess between them.

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 0%, so the description carries the full burden and does so: table is explained with alias semantics ("gems" = loose/unmounted, "jewelry" = finished/mounted, may span both), filters is defined as field/op/value dicts matching query_table with a concrete Patek Philippe example, and sold_only is given its default and effect. All three parameters gain meaning beyond the bare 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?

The first sentence states a specific verb and resource — summarize the realized-price market for a table or filtered segment — and the return list makes the output concrete (count, median, percentiles, min/max, vendor ranking). It does not explicitly distinguish itself from sibling aggregators such as market_index or price_trend, which an agent would still need to disambiguate.

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 a prerequisite ("call list_tables first") and explains when to pick "gems" versus "jewelry" and that a loose-stone question can span both, which is real usage context. However, it never says when to use market_stats instead of market_index, price_trend, or price_check, leaving the biggest selection question unanswered.

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