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

Annotations already mark this as read-only, idempotent, and non-destructive, and the description adds substantial context: no API key, nothing stored, no id issued, no record kept, deterministic behavior, hash-reproducible evidence, and assumptionsApplied returned in the response. This goes well beyond what the structured annotations alone communicate.

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 lead sentence is front-loaded with the core action and output, followed by a compact no-storage guarantee and practical sibling links. It is dense but not bloated; the only mild redundancy is the two-part emphasis that nothing is stored.

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, keyless tool with no output schema, the description covers determinism, response contents, input shape guidance, and persistence alternatives. It falls slightly short by not naming project_household and by giving only a high-level sketch of returned projection data, but the schema fills many remaining details.

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?

The description clarifies that household is 'a document you pass in' (not an ID) and notes that Monte Carlo is optional and seeded, and it points to list_example_households for the starting shape. However, it adds little about horizon, assumptions, or policy beyond what the schema already provides, and schema description coverage is only 60%, so those gaps are not fully compensated.

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 opens with a specific verb and resource: 'Run the deterministic multi-year household projection on a document you pass in,' and enumerates the computed outputs (income, RMDs, Roth conversions, taxes, expenses, amortization, deficit draw, net worth). It clearly distinguishes this keyless, stateless surface from create_household, which creates a persistent record, and points to list_example_households for input shape. The only minor ambiguity is that the sibling project_household is not explicitly referenced, but the core purpose is unmistakable.

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 explicitly routes to alternatives: 'Use list_example_households for a starting shape' and 'For a household that persists ... see create_household, which takes a key.' This gives clear context for when to use this ephemeral tool versus a persistent one. However, it does not mention the sibling project_household, so an agent may still be uncertain about the boundary between this tool and that one.

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