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

Annotations already declare the safety profile (readOnly, idempotent, closed-world, non-destructive), so the bar is lower. The description adds genuinely useful context beyond them: the data vintage (TY2022), that it is an aggregate federal statistic, and that it carries zero PII — all relevant for interpreting and trusting results.

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?

Two sentences, front-loaded with what the tool searches, followed by the return fields and the PII disclaimer. Dense but nearly every clause earns its place; the phrase 'Returns the 5-digit ZIP to pull its income/tax profile' is slightly awkward but not wasteful.

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 no output schema, the description usefully enumerates the returned metrics (returns, AGI, average AGI, wages, capital gains, EITC, charitable giving by AGI brackets) and the vintage year. Combined with annotations covering safety and scope, an agent has enough to call it correctly; only input-format specifics are left implicit.

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 100%, so both parameters (q and limit) are already documented with their formats and defaults. The description restates that q accepts a ZIP or state but adds no format or edge-case detail beyond the schema, so the baseline 3 applies.

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?

Names a specific data source (IRS SOI income statistics), a specific operation (search), and the two accepted scopes (ZIP code or state). The dataset is unique among siblings, so an agent can immediately tell this is the income-by-geography tool rather than any of the enforcement/patent/lobbying siblings.

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?

Usage is only implied — an agent can infer this is the tool for geographic income/tax profiles, and the stated ZIP-or-state scope hints at when it applies. However, there is no explicit when-to-use vs. when-not language, no mention of an alternative tool, and no guidance on required input format.

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