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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so safety is covered. The description adds real behavioral context beyond that: answers are ordered most-urgent-first with a tone (risk/warn/info), figures come from the Bazous engine, `focus_missing` is set when no answer exists, and single-topic queries return one card with a picture. It does not disclose anything about rate limits or audience/permission requirements.

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 example-question paragraph is front-loaded and useful, but the second paragraph is a long run-on list of covered topics that duplicates the enum in the schema, and the third paragraph repeats topic ids already given. It is verbose for what it communicates and would benefit from trimming redundancy.

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 an output schema present, return-shape explanation is not strictly required, yet the description still explains the key diegetic fields (headline, answers, all_clear, missing_data, focus_missing) and how filtering by `question` changes the result. Given the tool's breadth and complexity, it is complete enough to invoke correctly, with sibling differentiation remaining the notable gap.

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 description coverage is 0%, so the description must carry the load, and it largely does: it maps `question` to the full list of topic ids and their meaning (e.g., 'what-if (the payment the engine would move)', 'avoidable-fees (bank fees)') and states that `language` is fr/de/it/rm/en. Only `household_id` is left unaddressed, though its uuid format and optional default make it largely self-explanatory.

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 clear verb+resource (retrieve ready-made budget answers for a household) and enumerates the topics it covers, but it never distinguishes itself from close siblings like get_cash_safety_brief, get_household_snapshot, or get_upcoming_obligations, whose scopes visibly overlap with topics listed here (safety-cushion, available-now, due-before-payday). Without that differentiation an agent cannot reliably choose between them.

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 does give a usage instruction — call once, then call again with `question` set to a topic id for each follow-up — which implies a conversational loop. But 'use it for any question about the household's money' is so broad it actively competes with the sibling tools, and there is no explicit when-not or alternative routing.

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