price_trend

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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered; the description adds substantive behavior: the aggregation it performs, the time-bucketing behavior, and that sold_only restricts to sold lots with a positive USD price (default true) – a material effect on results. No auth or rate-limit context, and no note on sparse/empty periods.

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?

Front-loaded with the purpose, then an Args block that is easy to scan. Slightly redundant where it restates defaults already present in the schema (year, true), but those restatements are paired with clarifying semantics rather than pure duplication.

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?

An output schema exists, yet the description still summarizes the returned metrics (per-period sales count, median, average), which is enough for an agent to know what it will get. Combined with the parameter documentation and read-only annotation, nothing needed to invoke it correctly 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 description coverage is 0%, so the description carries the full burden and does so: it explains the table alias domain (Gems = loose stones, jewelry = mounted), the allowed 'by' values (year/quarter/month) which are absent as an enum in the schema, the filter shape referenced to query_table, and the precise semantics of sold_only. All four 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?

States a specific verb and resource ('Show how realized prices moved over time') and adds the exact computation performed (bucket sold lots by period, report count/median/average usd_price_decimal), which is more than a restatement of the name. It does not explicitly distinguish itself from siblings like market_stats or price_check, leaving the agent to infer the difference.

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 actionable prerequisites ('call list_tables first') and clarifies that filters use 'the same shape as query_table', which steers reuse of a known pattern. It never says when to prefer market_stats or price_check instead, so there is no explicit exclusion guidance.

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