Price history of a commodity

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

Annotations already declare readOnly/idempotent, but the description adds the non-obvious behavior an agent cannot infer: default window of the last 14 days, a hard 45-day cap, the trap that a wide filter silently returns only the 8 biggest symbols, and the fact that days without trades are absent from the series. Those truncation and coverage rules are exactly the kind of context structured fields don't carry.

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?

Four tight sentences, front-loaded with the resource and returned fields, then the usage case, then the constraints. It is dense but every clause carries information; only the slightly run-on constraint sentence could be split for readability.

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 compensates by naming all returned measures, and it covers the defaults, the maximum range, and the sparse-day caveat. An agent has enough to call it correctly and to predict what comes back, without needing anything else.

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 100%, so baseline is 3, but the description adds real semantic value: the 14-day default and 45-day ceiling for date_from/date_to, and the behavioral consequence of a broad filter. It still leaves main_cat / sub_cat / producer / cat unexplained beyond what the schema says (all four share an identical 'category id' description), which is the main residual gap.

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 resource (daily price series) at a specific grain (per symbol, over a date range) and even enumerates the returned measures (low, high, volume-weighted average, volume). It also relates itself to the sibling ime_trades ('Built from the trade list... Prices as in ime_trades'), so an agent can tell it apart from the raw-trades tool without opening a schema.

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 a concrete use case ('how did hot sheet / rebar / PE prices move this month') and tells the agent how to narrow results via sub_cat or search. It stops short of explicitly saying when to prefer ime_trades or ime_trade_stats instead, so routing against alternatives is implied rather than declared.

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