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

Annotations cover the safety profile, but the description adds substantial context they don't: NQ's non-continuity (weekend halt, 21:00 UTC break), that past windows are SEALED and safe to cache, and the no-key HTTP equivalent with its own parameter conventions. This is exactly the behavioral value structured fields cannot 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?

Front-loaded with the core action, then layers constraints, caching guidance, and the HTTP mirror without padding. Dense but every sentence carries information; slightly long for a four-parameter read tool.

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 should hint at return shape; it names 'real candles' and defers detail to the OpenAPI spec link. It covers continuity, sealing, and caching well, but the bar format itself is left to inference.

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% and both enums are documented, so the schema does the heavy lifting. The description notes the HTTP variant uses unix SECONDS versus the schema's ISO-8601, which is a useful distinction but not a semantics addition for the MCP parameters themselves.

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 ('Read real candles from the Taifoon tape for one market'), scoping it to a single market and a past window. This cleanly separates it from siblings like chart_image, chart_state, and forecast.

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 clear when-to-use context ('ground an answer in what the market actually did in a past window') and an explicit exclusion ('never to predict'). It does not name a specific sibling alternative to use instead, so it stops short of the top tier.

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