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

Annotations only cover safety flags (readOnlyHint=false, openWorldHint=false, destructiveHint=false); the description adds the important economic behavior — each call consumes a prepaid credit — and the gating rule that commit and pagination require a List pass token. That is real context beyond structured fields, though it omits what happens on failure (whether the credit is still charged) and what a 'committed report' actually changes.

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?

Two tight sentences with the cost model front-loaded and no filler. It is efficient, though the phrasing is dense enough that the pass requirement reads as an afterthought rather than a clearly scoped condition.

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 seven parameters, 43% schema coverage, no output schema and only safety annotations, the description should explain what a query returns, which website/scope it covers, and the offset/pagination format. It covers the credit and pass economics but leaves the agent guessing about output shape and the semantics of four parameters.

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 43%, so the schema documents only payer, creditKey and passToken; meta, commit, query and nextOffset are undocumented. The description hints at commit ('committed reports') and passToken ('Basic or Pro List pass'), but adds nothing about meta or the format of nextOffset, so it only partially compensates for the coverage 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 and resource: 'Natural-language website query' plus the billing model ('using one prepaid credit'). An agent can tell it is a paid, single-shot query endpoint, but the description never distinguishes it from siblings like ask-api or ask-api-json, so differentiation must be inferred from names alone.

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 implied rather than stated: it tells you a call costs one credit and that committed reports and pagination additionally need a Basic or Pro List pass, which is a useful precondition. However, it never says when to choose this over the free/JSON variants or when a List pass is genuinely required versus optional, leaving the routing decision to the agent.

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