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

Annotations already declare readOnly=true, idempotent=true, and destructive=false; the description adds valuable behavioral context: it uses exact decimal arithmetic, does not fetch vendor pricing, and mentions the price per completed bounded job. It does not detail edge cases like rounding failures or error behavior, but the key non-obvious traits are disclosed.

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?

The description is compact and front-loaded with the core action, then the critical exclusion, then pricing. It earns its place, though the pricing sentence could be considered slightly tangential to invocation correctness.

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 computation tool with no output schema, the description communicates the core contract: input is tariff + usage, output is a recomputed bill, and optional invoice comparison. It lacks explicit statement of return format or failure conditions, but given the detailed input schema and annotations, this is a strong definition.

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 description coverage is only 20%, so the schema leaves most parameters underdocumented; the description mentions graduated tiers, included allowances, fixed charges, aggregated usage, and optional invoice total, which maps to the parameters at a high level. It does not add details like decimal limits or the meaning of `up_to: null`, but it gives enough conceptual grounding for an agent to understand the input shape.

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 clearly states what the tool does: recompute a usage-based bill from customer-supplied tariff and metered usage, using exact decimal arithmetic. It also explicitly distinguishes itself by stating it does NOT fetch or embed vendor pricing, which prevents misuse.

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?

The description explains the tool applies only caller-provided rules and optionally checks against an invoice total, giving clear context for when to use it. It does not explicitly name alternatives because there are no siblings, but it conveys the boundary of responsibility well.

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