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

Annotations already establish readOnly, idempotent, non-destructive, closed-world behavior, so the safety bar is pre-cleared. The description adds genuinely new context: monthly compounding default with four alternatives on request, and that the return includes a plain-English explanation, stated assumptions, and a matching calculator page URL. It just doesn't say anything about the boundaries that produced the worked example's assumptions.

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 trigger condition and examples are front-loaded, then the computation is defined, then the return shape — a sensible order with no filler sentences. The worked example at the end ($10,000 at 7% for 10 years = $19,671.51) is defensible as a verification anchor but is the one piece that could be trimmed without loss.

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 7-parameter, annotation-covered, no-output-schema calculator, the description covers what is computed, the default compounding assumption, the return contents, and a sanity-check value — enough to call it correctly. Minor gaps: it never mentions the begin/end deposit timing or the year-by-year table option, leaving those purely to the schema.

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% with per-field descriptions, defaults, ranges, and examples, so the baseline of 3 applies. The description's parameter-adjacent text ('starting amount plus optional monthly contributions at a yearly rate', 'monthly by default... on request') largely restates the schema rather than adding semantics; contribution_timing and show_yearly are never touched in prose.

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 names a specific computation and its exact scope: future value of a starting amount plus optional monthly contributions at a yearly rate, with total contributed and total interest. The three paraphrased user questions make the resource boundary concrete, so an agent can distinguish it from siblings like rule_of_72 or calculate_savings_goal 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 opens with an explicit 'Use when a user asks...' trigger and three representative phrasings, which is strong positive guidance. It stops short of any exclusion or sibling routing (e.g., when to prefer rule_of_72 for doubling time or calculate_savings_goal for a target), so the alternative-selection half of the guidance is missing.

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