get_housing

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It confirms this is a read operation (getting median home price), but doesn't disclose data freshness, what time period the median reflects, potential missing-data behavior, or whether the price reflects current listings vs sold values. Without annotations, more behavioral context would be expected.

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?

Single sentence, extremely efficient - 'Median home price for one town, in USD.' covers purpose, scope, and unit with zero wasted words. No redundancy with the name or 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?

For a simple single-parameter read tool, the description is mostly adequate. There is no output schema, no annotations, and 0% schema coverage, so the description carries the entire burden. It tells the agent the return value conceptually (median home price in USD) but leaves uncertainty about date range, data recency, and edge cases. Given the simplicity of the tool, this is near-minimum-viable but has noticeable gaps.

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?

There is one parameter (town) with 0% schema description coverage, meaning the schema property has no description beyond its name. The description states the town is a single town (scope), which adds some meaning, but doesn't clarify expected format (e.g., 'Springfield, MA' vs 'springfield'), case sensitivity, or valid range of town names. With only one param, the baseline credit is partially earned but minimal guidance is given.

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 'Median home price for one town, in USD' clearly states the verb+resource (get median home price) and adds the scope constraint 'one town'. It distinguishes from siblings like get_distance, get_schools, get_safety which cover different domains. However, it doesn't explicitly name the alternative tools, slightly limiting differentiation.

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 implies usage in the context of querying housing cost data for a single town, and the sibling tool names (get_distance, get_schools, get_safety) suggest the broader context of town comparison. However, there are no explicit when-to-use or when-not-to-use instructions, nor any exclusions or alternatives named.

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