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

The annotations already declare readOnlyHint=true and destructiveHint=false, which covers the safety profile (no mutation). The description adds behavioral context beyond annotations by specifying that each suggestion carries a stable key, payee, amount, cadence, confidence, and charges behind it, giving the agent a sense of what to expect. However, it does not disclose any edge cases, limits, or return behavior (e.g., if no suggestions are found), but given the strong annotation coverage, this is acceptable.

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 two sentences long, with the first sentence front-loading the core purpose and key types of suggestions, and the second sentence listing the important fields without excessive detail. It is concise and focused, though it could arguably be split into a more digestible structure, but it is neither verbose nor wasteful. The purpose is stated upfront, with the next step mentioned at the end.

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?

Given that the tool is a read-only list with a single optional parameter, the description is complete: it clarifies the two kinds of suggestions, the fields available on each, and offers the next step (accept_recurrence_suggestion). The absence of an output schema is compensated by listing the fields. There is no missing information that an agent would need to call it correctly, aside from perhaps what happens when there are no suggestions, which is minor.

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 has 100% coverage, with a description for the only parameter (householdId) that explains its purpose and optionality. The description adds no additional parameter information beyond what's in the schema)Skip; it does not clarify anything about householdId beyond Schema. Since schema covers the parameter fully, a score of 3 (baseline) is appropriate.

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 specifies a precise verb ('List'), a clear resource ('recurring charges detected in household activity'), and scopes the types of charges (un-scheduled 'new' kinds and 'price_change' recurrences). This clearly distinguishes it from the sibling tool list_recurrences, which likely lists scheduled recurrences. The description immediately conveys what the tool does and its scope.

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 states the tool lists detected recurring charges and mentions that the listed items are those that are 'not scheduled yet' and those with price changes, which implies it should be used when you need to review detected suggestions before scheduling. It does not explicitly state when not to use it or name alternatives, but the reference to using accept_recurrence_suggestion for scheduling provides a clear next step, and the scope of 'detected' charges is implicit guidance. Could benefit from explicit exclusion of already-scheduled recurrences, but the context is mostly clear.

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