tax_regime_lookup

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

With zero annotations, the description carries the full burden and exceeds it: it discloses the return format (decimal strings), the inclusion of every statute citation, the requires_competent_human_review=true flag, the refusal-by-type behavior for unknown states, and even the design rationale for declaring the argument optional. This is unusually rich behavioral disclosure for an MCP tool.

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?

Four sentences, front-loaded with the core purpose, and every clause earns its place. The parenthetical explaining the optional-argument design is verbose but materially important for correct invocation. Slightly dense, but not padded.

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?

The description thoroughly covers output content and refusal behavior, which matters because there is no output schema and no annotations. But with 8 parameters at 0% schema coverage, the input semantics for seven parameters are left to inference, and there is no statement of how parameters combine per state — a meaningful gap for a tool this complex.

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 0%, so the description must compensate, but only the state parameter is explained — its supported values, refusal behavior, and optional-argument rationale. The other seven parameters (tax_year, just_value, unit_count, school_millage, non_school_millage, prior_assessed_value, ownership_change_or_qualifying_improvement) are never tied to the assessed-value computation, so an agent cannot know how inputs map to the returned schedule.

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 first sentence states a specific verb+resource: a statute-cited property-tax regime schedule for explicitly named supported states (TX CA FL AL). It is unmistakably distinct from the sibling tools, which are all component/underwriting/renovation tools, so an agent can select it correctly without opening any schema. The refusal behavior for unsupported states further pins down scope.

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 names the exact supported jurisdictions and states that unknown states are refused, giving clear when-to-use guidance. It adds the human-review caveat so the agent knows this is research, not legal advice. It doesn't name an alternative tool by name, but no sibling offers a tax-regime lookup, so an explicit exclusion is unnecessary.

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