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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds real value beyond them: it discloses that no computation occurs, that the return includes a one-line explanation per field, and what the default example persona is. It doesn't describe the overall structure or size of the returned object, which keeps it from a 5.

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?

Four short sentences, front-loaded with the return value, then the no-solve caveat, then the action, then parameter notes. Dense and functional, with only mild redundancy between the title-style phrasing and the body.

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 must explain the return, and it does: a complete example input plus one-line explanations of every field. For a single-optional-enum, read-only helper this is nearly sufficient; only the rough shape/size of the returned example 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 coverage is 0%, so the description carries the burden, and it does: it documents the enum values 'single' and 'married' and names 'single' as the default with a concrete persona (60-year-old early retiree, traditional IRA, brokerage, later Social Security). 'married' is named but its variant contents are not described, leaving a small gap.

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?

Specific verb and resource: returns a complete example input for the named sibling tool optimize_roth_conversions, including per-field explanations. The 'No solve' sentence immediately separates it from the actual optimizer, so an agent can distinguish it from optimize_roth_conversions 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?

States the workflow clearly: fetch this template, then edit it to the user's situation, and explicitly that no solve happens here. It doesn't mention check_request or say when a caller should skip this and construct input directly, so there is no explicit exclusion, but the usage context is unambiguous.

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