vedika_usage

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

With no annotations, the description carries the full burden and does so well: it discloses the unit convention (USD cents, divide by 100), the source-data ceiling (at most 1000 latest records) that silently bounds both history and aggregates, the absence of cursor/page continuation, and the specific response fields (truncated, scanLimit) that signal when results are incomplete. That last detail is the difference between an agent reporting bounded data as complete and not.

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?

Six tight sentences, each carrying a distinct fact: purpose, unit conversion, history bounds, no-pagination constraint, aggregate ceiling with sentinel fields, models grouping, and cost. Purpose is front-loaded and no sentence is filler, even where it overlaps the schema slightly.

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, so the description must cover return values, and it partially does by naming truncated and scanLimit and explaining the cents unit and tier grouping. It doesn't sketch the overall shape of wallet/history/summary responses, leaving some ambiguity about what fields come back, which keeps it just below full completeness.

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 100%, so both parameters are already documented, including the action enum meanings. The description restates the limit default/maximum and adds context that limit applies to history only, but does not add syntax or behavioral nuance the schema lacks. Baseline 3 applies when the schema does the heavy lifting.

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 resources: checking API usage, wallet balance, and billing history, plus the four action modes the tool serves. Against a sibling list composed entirely of astrology/Vastu domain tools, this is unambiguously the account/billing utility, so an agent can select it 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?

Makes the cost profile explicit ('Free — no cost to check'), which is exactly the kind of guidance that decides whether an agent should hesitate before calling. It also flags the absence of pagination up front so the agent doesn't plan a paging loop. It stops short of naming alternatives or stating when not to use it, though no sibling offers comparable functionality.

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