createTaxReport

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

Discloses traits well beyond the annotations: async task semantics, the `queryId` return value and how it is used downstream, a 2-month interval cap, concurrency limits with a duplicate-submission warning, and an eligibility restriction. This is consistent with destructiveHint=true and the required `confirm` gate rather than contradicting it.

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 return value are front-loaded in the first sentence, then parameter notes, a lookup table, and operational caveats follow in a scannable order. The long table is load-bearing reference data that the schema does not supply, so every line earns its place.

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?

No output schema exists, and the description compensates by naming the returned `queryId` and the downstream status/URL steps. Combined with the enum coverage table and eligibility/limit notes, an agent has everything needed to invoke this correctly.

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?

With schema description coverage at only 20%, the description carries the burden and does so well: it expands the bare `number` string into a full 22-row type+number category table and states the `{type}-{number}` composition rule plus the startTime/endTime interval constraint. It omits units/format for `startTime` and `endTime`, which is the only meaningful gap.

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+resource ('Create a tax report file generation task') and immediately clarifies the async nature and the returned handle (`queryId`). An agent can distinguish this from siblings like `getTaxReportStatus` or `batchCreateTaxReports` without opening the schema.

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 follow-up guidance ('poll the Status endpoint after creation'), a duplicate-request warning, and an explicit exclusion ('Institutional customers are not allowed to use this endpoint'). It stops short of naming the sibling tools (`getTaxReportStatus`, `getTaxReportUrl`) directly, so routing is clear but not maximally explicit.

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