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

Annotations already cover safety (readOnly, idempotent, non-destructive), so the description's job is data provenance — and it delivers: HUD FY2026 vintage, MTSP dataset, HERA Special "where HUD lists them," and the IRS Pub. 5913 rent-derivation method. It only lacks failure behavior (e.g., what happens on ambiguous or non-covered counties).

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 the data vintage and scope, and the location-input instruction is separated out where it is easy to find. The first sentence is a dense enumeration but every clause names a distinct returned dataset, so nothing is padding.

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 carries the return-value burden and does so completely: levels, household sizes, HERA variants, AMI, and rent by bedroom. An agent knows exactly what it gets back and whether to supply names or a FIPS code.

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 coverage is 100%, so baseline is 3; the description still adds value by framing the defaults — the full 20-80% range across 1-8 persons is returned unless narrowed — which explains the optional ami_level and household_size filters. It also restates the state+county-or-fips input pattern that the schema documents separately per field.

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 (HUD FY2026 MTSP income limits for a county/town) and then enumerates the exact contents: 20%-80% AMI levels, 1-8 persons, HERA Special, AMI, and max gross rent by bedroom. That enumeration distinguishes it from calculate_max_rent and get_applicable_percentages, which compute rather than retrieve.

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?

"Give state + county, or fips" covers how to supply location, but there is no explicit when-to-use guidance and no routing away from overlapping siblings such as calculate_max_rent or get_applicable_percentages. Usage is inferable from the payload list rather than stated.

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