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

Annotations already mark it read-only and non-destructive, so the description's job is to add context. It adds useful behavioral disclosure: the tool combines recent market movement windows (1w/2w/4w) with payment and break-even math, and produces a documentable recommendation rather than a forecast. No contradiction with annotations is present.

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 sentences with no filler. The core purpose and scope are front-loaded, the relationship to a sibling is stated succinctly, and the key exclusion ('Not a rate forecast') is a single short closing sentence. Every sentence adds value.

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 complex 10-parameter tool, the description covers the decision context, required inputs, analytical approach, output nature, and sibling differentiation. The presence of an output schema and rich property descriptions means the description does not need to enumerate return fields or defaults; what remains is adequate for an agent to invoke correctly.

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?

With 80% schema description coverage, the schema carries most parameter documentation. The description adds meaning by identifying which parameters drive the decision (lock-expiration date, locked rate, float-down cost) and by explaining the analytical intent (payment and break-even math on this loan). This goes beyond raw schema labels.

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 a specific resource ('lock-vs-float-down recommendation') and audience/context ('deal already in the pipeline'), with a clear verb-like outcome ('returns a defensible hold-lock vs exercise-float-down call'). It explicitly differentiates from sibling assess_buy_timing by noting it builds on the same signal but is framed around the lock window/expiration.

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 gives clear context for when to use the tool: when a deal is already in the pipeline, a lock-expiration date is known, and the analyst needs a documented hold-lock vs float-down decision. It also says what it is not ('Not a rate forecast') and distinguishes it from assess_buy_timing, though it does not explicitly list exclusions or name the exact alternative condition.

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