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

Goes well beyond the annotations by disclosing the exact price ($0.005, product nvd.cve), that charges are drawn in USDC from a wallet, that budget caps apply, and that results are third-party data rather than instructions — a real prompt-injection warning. It also implicitly explains why readOnlyHint=false despite being a lookup: every call has a payment side effect. It does not state whether a failed or empty result still incurs the charge.

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-loads what the tool returns, then payment terms, then the free-sample escape hatch — the ordering an agent needs. Each sentence carries distinct information (price, currency, budget, injection warning, alternative), though the payment clause is stated in two overlapping ways that could be merged.

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?

For a paid, open-world lookup with no output schema, the definition covers cost, billing mechanism, budget behavior, trust level of the returned data, and a free preview alternative — everything needed to decide whether to call it. It stops short of describing result shape or pagination/limit behavior, which an agent must discover empirically.

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?

Coverage is 50%, and the description only clarifies that lookup works 'by id or keyword', mapping loosely to id and q without stating whether they are mutually exclusive, combinable, or which wins. The limit and confirm_over_cap semantics are left entirely to the schema, so the description adds only modest meaning beyond structured fields.

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?

Names the resource precisely (CVE records from the US National Vulnerability Database) and the two access modes (by id or keyword), so an agent knows exactly what it retrieves. It does not explicitly distinguish itself from structurally similar siblings such as patent_lookup or company_lookup, leaving the domain distinction to inference from the data source name.

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?

Explicitly routes the agent to free_sample before paying, which is the key decision point for a metered tool. It does not explain when to choose 'id' versus 'q', or that one mode is likely preferred for exact lookups versus browsing, which is the remaining gap.

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