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

Beyond the readOnlyHint and openWorldHint annotations, the description reveals deterministic behavior, the compiled corpus limit, the polarity-checking mechanism, and a named-example ledger. It explicitly warns that an absence of flags only means no contradiction with compiled law, not a general approval. This is rich behavioral disclosure that goes well beyond the structured annotations.

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 a single, well-structured paragraph with four sentences, each earning its place: the main function, an example, a crucial caveat, and a usage directive. The case-name parenthetical is informative without being excessive, and key warnings are highlighted with 'IMPORTANT'.

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?

Given the tool's complexity and the absence of an output schema, the description covers the behavior, scope, limitations, and usage context thoroughly. The only minor gap is that it does not describe the exact return format (e.g., list of flags), but the caveat about 'no flags' implies a flag-based response, which is likely sufficient for an agent to invoke it correctly.

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?

The schema covers both parameters completely, so the baseline is 3. The description adds valuable extra semantics by giving a sentence-format example for the 'text' parameter and clarifying that 'as_of' relates to validity windows. This enriches the meaning beyond field descriptions.

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 opens with a specific verb ('deterministically verify') and resource ('a piece of tax analysis'), then enumerates the exact checks performed (citations, quotes, thresholds, temporal claims, case holdings). This clearly distinguishes it from sibling tools like analyze_cross_border_tax or lookup_compiled_rule, which have different purposes.

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 explicitly states when to use the tool ('Use before relying on or presenting any cross-border tax reasoning') and also gives a critical exclusion ('it is NOT a confirmation of claims outside the compiled corridors'). This provides both when-to-use and when-not-to-trust guidance, exceeding a simple context hint.

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