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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the bar is lower. The description still adds useful context beyond them: the decision logic is a three-question chooser sourced from a specific site, and a negative outcome ('not FHA yet') is a legitimate result an agent should expect rather than treat as an error.

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?

A single sentence, front-loaded with the verb and the source, then the return payload. Dense but every clause carries information; the parenthetical program list is the only part that runs long, and it earns its place by defining the output space.

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 covers the return values (likely program, reason, next page to read). The conditional parameter logic is fully handled by the schema. Only the sequencing relative to the sibling pricing/sizing tools is left unstated.

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%, with conditional applicability ('only when has_fha_loan is true') and defaults already documented per parameter. The description adds nothing beyond that, so the baseline of 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?

States a specific verb and resource ('runs the three-question FHA multifamily program chooser') and enumerates the possible outputs (223(f), 221(d)(4), 223(a)(7), 241(a), or 'not FHA yet'). That is clearly distinct from the siblings get_limits_and_costs and size_loan, which do not select a program.

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 implied: an agent should call this to route an owner to a program before pricing or sizing. But the description never says when not to use it or how it relates to the sibling tools (e.g., run this first, then size_loan). No explicit prerequisites or exclusions.

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