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

With no annotations, the description carries the full load and does well: it discloses data freshness (frozen daily at 20:00 Hong Kong), tamper-evidence (hash chain), methodology (matched-model so new platform listings are not counted as price cuts), base period = 100, and licensing/citation obligations (CC BY 4.0, DOI). It still omits any mention of rate limits or how stale an intraday query would be relative to the last freeze.

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?

Purpose and scope are front-loaded in the first clause, followed by sub-index definitions and methodology. It is dense but mostly earns its space; the trailing data-URL, license, and DOI are citation metadata rather than invocation guidance, so they add some bulk for an agent that only needs to call the 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?

An output schema exists, so return-value explanation is unnecessary. For a one-parameter read-only index lookup, the description covers what is measured, how it is computed, the sub-series breakdown, refresh cadence, and provenance — nothing an agent needs in order to call it correctly is missing.

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% (the single 'days' parameter has no description), so the description must compensate. '近 N 日走势' plus the example ghpi_index(days=30) makes clear that days sets the trend window, which is more than the schema conveys; the default of 30 is only visible in the schema, not the text.

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 opens with a specific verb and resource ('查询 GHPI ... 的最新值与近 N 日走势') and enumerates the three sub-indices (GHPI-H100, GHPI-CN, CDI), so the agent knows exactly what data comes back. It does not explicitly distinguish itself from siblings like gpu_price or gpu_history, leaving the agent to infer that this returns an index rather than raw prices.

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?

Usage is only implied: '免费' plus the example call ghpi_index(days=30) suggest a free trend lookup, and the raw-series URL hints at an alternative for full data. There is no statement of when to prefer this over gpu_price, gpu_history, or bulk_export_series, and no exclusions or prerequisites.

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