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

Annotations already declare readOnly/idempotent/closed-world, but the description adds real value: it discloses the return content ('arithmetic and withheld-cash reasons') and explicitly disclaims side effects and verification ('no fetch, storage, execution or verified balance'). This tells the agent the result is unverified arithmetic, which the annotations alone do not convey.

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 core purpose and tightly packed into three sentences with no filler. The telegraphic 'Decimal strings:' fragment is efficient, though slightly cryptic for a first-time caller.

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 17-parameter tool with no schema descriptions and no output schema, the description covers the numeric units and clock format but omits the semantics of the boolean gating flags and the shape of the 'withheld-cash reasons' output. It is a helpful partial guide but not complete enough to invoke confidently without guessing.

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 0% across 17 parameters, so the description must compensate and only partially does. It supplies units and format for the numerics (kg, fineness in (0,1], USD/troy-oz bid, USD fees, currency/USD FX with USD=1) and the 'aware ISO clocks' format for the timestamp fields, but leaves fx_fee_bps, quote_currency, and the gating booleans (cleared, access_restricted, pledged) unexplained despite 'cash gates' being central to the tool.

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 ('Calculate') and resource ('gold sale proceeds and cash gates') and scopes it as a pure computation ('from caller inputs'). It does not explicitly name or differentiate itself from calculation-adjacent siblings such as exit_cost or crypto_exit_check, but the gold-sale framing is specific enough to route an agent.

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?

The phrase 'from caller inputs' and 'no fetch, storage, execution or verified balance' imply this is a deterministic what-if calculator rather than a data source, which is useful context. However, it never states when to prefer this over alternatives like exit_cost or unwind_watch, nor any exclusions or prerequisites for the scenario.

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