shelter_ask

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

Annotations already disclose readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, so the agent knows this is a safe, non-mutating, open-ended query. The description adds examples of the type of questions (spending, bills, trends, advice) but does not disclose any limitations, response format, or potential for non-financial queries. Since annotations cover the safety profile, the additional context is modest but not contradictory.

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 one short sentence that immediately conveys the purpose. It is front-loaded with the main verb and object, followed by clarifying examples. There is no redundancy or filler, making it highly efficient for an agent to parse.

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 single-parameter, read-only, open-world Q&A tool, the description provides sufficient context to understand its role. It does not mention the response format (e.g., whether the answer is text, JSON, or includes warnings), but given the simplicity and the annotations, this is not a critical gap. The tool's position among specialized siblings is clear, and the description is complete enough for an agent to select it appropriately.

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% for the single 'question' parameter, which already states 'A natural-language question about your finances.' The description adds value by providing concrete examples of query categories (spending, bills, trends, advice), enriching the meaning of what a valid question might contain. Though the baseline for full coverage is 3, the examples elevate understanding of the parameter's intended usage.

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 clearly states what the tool does: 'Ask Guardian AI any question about your finances.' The verb is specific ('ask'), the resource is identified ('Guardian AI', your finances), and the examples (spending, bills, trends, advice) outline the scope. It also naturally distinguishes itself from sibling tools, which are more specialized (e.g., shelter_status, shelter_runway), by positioning this as a general-purpose assistant.

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 implies the tool is for general finance questions, but it does not explicitly say when to use it over the specialized sibling tools (e.g., shelter_status for status, shelter_forecast for forecasts). The phrase 'any question' suggests a fallback, but no alternative tools are mentioned or excluded. Usage context is thus implied rather than stated.

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