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

Annotations already cover read-only, idempotent, non-destructive, closed-world behavior, yet the description adds genuinely useful behavior: multiple quote tiers (highest price fitting every bar, prices fitting only some bars such as 2026 Antam), per-quote dealer and day, and a world-gold-price estimate fallback when no dealer lists the brand. The garbled clause 'when no dealer FiLot reads prices the brand' obscures part of the fallback logic.

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 intent is front-loaded, but the body is one dense run-on sentence and contains a corrupted phrase ('when no dealer FiLot reads prices the brand'), which costs clarity. There is real information here, but it is not cleanly structured.

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 return-shape burden and largely does so: it enumerates the highest price, partial-fit prices with dealer and day, and the estimate fallback. Combined with full schema coverage of the three inputs and solid annotations, an agent has enough to call and interpret the tool.

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 baseline is 3, but the description goes beyond the schema by tying the brand parameter to concrete coverage behavior (which brands have dealer prices, which fall back to an estimate) and by emphasizing that grams refers to exactly ONE bar. This adds decision-relevant meaning the enum-free brand schema does not convey.

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 (buy back / pay), resource (one gold bar of a given brand and weight), and currency (rupiah), so an agent can tell it is about dealer buyback quotes rather than spot price or tax. It does not name or contrast with siblings like gold_price_sources, so differentiation is only inferable from content.

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?

Implies the context well: it is the tool to use when you need what Indonesian dealers pay today for a single bar, and it explains the two regimes (brands with dealer prices vs. brands that fall back to a world-price estimate). No explicit when-not-to-use or alternative-tool routing is given.

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