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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower; the description still adds valuable context beyond them — the ACS 2020–2024 5-year vintage, the HUD 30%/50% cost-burden standard and which programs rely on it, and the dual input modes. It does not discuss latency, caching, or behavior when a tract has no data, which would be the remaining behavioral gap.

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?

Front-loads the metric inventory, then the domain rationale, then the input modes — a sensible order with no filler sentences. It is a dense single paragraph, and the metric list is long, but each clause maps to real return content the agent needs since there is no output schema.

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 correctly compensates by naming the metrics returned. All four parameters are optional (required: 0), yet the description never states which combination is actually needed to resolve a tract — an agent could plausibly call it with no arguments. That is the one material gap in an otherwise complete 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 100%, so the schema already documents all four parameters, including resource_id as an 'Alternative' lookup. The description's 'Accepts either FIPS codes or a resource_id' restates that alternation without adding format rules (e.g., whether state+county+tract must all be supplied, or what happens if both modes are given). Baseline 3 is appropriate.

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 and resource ('Get tract-level housing-cost overlay') and enumerates the exact metrics returned (median rent, home value, 30%+/50%+ rent burden shares, median income). It is clearly separable from siblings like get_tract_demographics and find_high_housing_burden_tracts.

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?

Gives concrete use cases ('qualify a veteran for housing aid, contextualize a service location, or find tracts with high rent burden'), which tells the agent when this tool applies. However, it never names or distinguishes itself from the obvious sibling find_high_housing_burden_tracts, whose name suggests overlapping purpose, so the routing decision between the two is left ambiguous.

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