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

Beyond the annotations, the description discloses important behaviors: no API key, nothing stored, no id issued, deterministic output, and a reproducible evidence hash. It explains that the response includes assumptionsApplied and an evidence record, which is valuable context the annotations alone do not provide.

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 description is dense but well organized: action first, followed by key constraints, response contents, and usage alternatives. It is longer than the minimum, but almost every sentence carries useful information, with only minor flourish like 'so you can show your work.'

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 tool with nested objects and no output schema, the description is complete enough for an agent to invoke it correctly. It describes what the response will contain, how results are reproducible, that no storage occurs, where to find an example input, and the persistent alternative.

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 schema already provides descriptions for household, monteCarlo, and assumptions, covering 60% of parameters. The description adds high-level context like 'document you pass in' and 'seeded Monte Carlo,' but it does not add significant meaning for the policy or horizon parameters beyond what their names and schema structures imply.

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 lists the concrete outputs such as income, RMDs, Roth conversions, and net worth per year. It also distinguishes itself from persistent household tools by emphasizing that no household is created, no id issued, and no record is kept.

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 explicit usage context: this is the keyless, stateless projection surface, while 'For a household that persists — with an id, bulk import, webhooks and drift detection — see create_household.' It also directs users to list_example_households for a starting shape, clearly guiding tool selection.

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