analyze_token_discount

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

With readOnlyHint=true and openWorldHint=false already covering safety, the description adds rich behavior: it contrasts fee calculations with and without the token, explains exchange-specific discount ladders, discloses return values (annual USD saving, opportunity cost, payback months, max absorbable drop), and states the default snapshot behavior and override. No annotation contradiction.

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 description is front-loaded with usage triggers and then systematically covers computation, outputs, defaults, and required inputs. However, the Chinese and English trigger sentences are largely duplicated, and the remainder is long, so it is information-dense but not optimally concise.

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?

There is no output schema, so the description must carry return-value disclosure, and it does: annual USD saving, opportunity cost, payback months, maximum price drop, and the all-tiers table when tokenBalance is omitted. It also covers required inputs and default behavior, making it complete for an agent to invoke this complex analytical 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 adds meaning beyond the schema by mapping supported exchanges to token behaviors, clarifying that tokenBalance omission returns all reachable tiers with a recommended best-payback tier, and explaining tokenPriceUsd as an explicit override of the 2026-09 snapshot.

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 description states a specific analytical purpose: computing whether holding an exchange's native token for fee discounts pays back, including annual savings, opportunity cost, payback months, and max price drop. It names the supported tokens (BNB/GT/KCS/BGB/MX/HYPE) and discount mechanics, making it easy to distinguish from generic fee-savings siblings like calculate_savings or calculate_annual_cost.

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 explicit trigger conditions: when the user asks whether holding an exchange token is worth it, how long until payback, or how far price can drop. It does not name alternative sibling tools or state when not to use this tool, so it falls short of full when/when-not/alternatives guidance.

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