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

Annotations already declare a safe, read-only, idempotent, closed-world operation. The description adds domain-meaningful behavioral context beyond that: the 1.75% upfront MIP, the 0.50-0.55% annual MIP, and that the output includes tax and insurance side-by-side with a conventional loan. It does not describe output structure, but with annotations covering the safety profile and no output schema expected, this adds genuine value.

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?

Three short sentences with the core calculation facts front-loaded and the comparison framing stated early. The trailing web-page URL is slightly promotional filler but harmless, so the text is largely efficient.

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 10-parameter, no-output-schema calculator with read-only annotations, the description supplies the key domain context (what MIP is included, that tax/insurance are in the result, and the conventional comparison) needed to call it appropriately. It could note the return format, but the absence of an output schema and the annotation coverage limit how much more is required.

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 all 10 parameters are already documented in the schema. The description merely echoes a few of them (3.5% down, tax, insurance) without adding syntax, ranges, or format detail beyond what the schema provides, 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?

The description states what the tool computes (FHA monthly payment including MIP, tax and insurance) and differentiates it from a conventional loan calculation, which distinguishes it from the many mortgage/loan siblings. The verb is implicit ('See the full monthly cost') rather than an explicit 'calculate', but the resource and scope are clear enough to select it without opening the schema.

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?

It implies usage by contrasting FHA with a conventional loan ('beside a conventional loan'), so an agent can infer this is for FHA-vs-conventional comparison, but there is no explicit when-to-use statement or named alternative (e.g., mortgage_calculator or conventional mortgage tools). Guidance is present but left to inference.

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