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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the description's 'stores nothing and files nothing' largely reinforces them. It does add genuinely new context beyond the annotations: the single-quarter data coverage limit, the fact that output is an estimate computed with the same maths as the public calculator, and an explicit non-tax-advice / not-a-filed-return caveat. No return format or precision detail is given, so not a 5.

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?

Five sentences, all load-bearing, with the core capability front-loaded before the estimation condition, data-coverage limit, and disclaimer. The opening sentence is dense with a three-item list but the structure remains scannable; only minor trimming is possible.

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 only three parameters, full schema coverage, and annotations carrying the safety profile, the definition covers what an agent needs to select and call it correctly, including a mutation-free guarantee and a hard data-recency limit. It leaves the shape of the estimate response (fields, currency, rounding) implicit, which is a modest gap in the absence of an output schema.

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 the parameters are already well documented; the description still adds the causal relationship the schema cannot express, namely that supplying jurisdictions with miles and gallons is what activates the estimate rather than an answer-only response. The Diesel default and jurisdiction semantics remain schema territory, keeping this below 5.

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 (answers) and resource (US/Canadian IFTA fuel-tax questions) and enumerates the exact question classes covered: due dates, quarterly reconciliation mechanics, and per-jurisdiction tax/surcharge rates. The scope is narrowed to Q3 2026, so an agent knows precisely what domain this covers and where it stops.

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 states the trigger for the estimation path ('If miles and gallons per jurisdiction are given, it estimates the quarter's tax owed or credit') and sets a hard boundary ('Only Q3 2026 rates are loaded'), which tells the agent when this tool will not answer. It stops short of naming an alternative for other quarters, but no sibling tool exists to route to.

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