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

Annotations already declare readOnlyHint/idempotentHint/destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds real behavioral context: it names the underlying methodology ('Uses the site's own math'), specifies that output is an itemized comparison against typical lenders, and documents that Spanish responses come back with legal disclosures kept in English verbatim.

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?

The purpose is front-loaded in the first clause, and the enumerated savings components each carry information an agent cannot get from the schema. It runs as one dense block and the trailing 'Answers in Spanish with language=es (ahorros)' feels appended rather than integrated, but there is little outright waste.

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 9-parameter estimator with no output schema, the description does the heavy lifting: it tells the agent exactly what the response will contain (itemized lender vs CapCenter closing costs, purchase credit cap of 0.5%, listing-fee differential and minimum, insurance statement). Combined with 100% schema coverage and read-only annotations, an agent has everything needed to call it correctly and interpret the result.

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 every parameter including the goal enum, county slug format and language behavior. The description reinforces the county-scope constraint and the language=es behavior, but adds no syntax or conditional guidance beyond what the schema states, so baseline 3 is correct.

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 ('Estimate') and resource ('what a client saves with CapCenter'), then enumerates the four goals and the exact components returned: lender closing-cost comparison, Realty Purchase Credit, 1% Listing Fee, insurance savings. This is specific enough that an agent can distinguish it from get_affordability_estimate, get_home_value_estimate and compare_refinance_options without opening any 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?

Usage context is implied by the goal list (buy, sell, sell-and-buy, refinance) and the 'county CapCenter serves' constraint, which mirrors the required parameters. However, it never routes the agent against siblings: there is no statement of when to prefer get_affordability_estimate or compare_refinance_options, nor any exclusion such as 'not for pre-qualification or rate quotes'.

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