Analysis — Recurring charges

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

Annotations cover the safety profile (readOnly, non-destructive, closed-world), and the description adds substantial context beyond that: grouping is by payee id rather than name, outflows-only filtering, transfer exclusion, the 3-charge recognition threshold, per-result fields (occurrences, amount_changed, days_since_last), and the milliunits unit convention. This is exactly the operational detail an agent needs to interpret results correctly.

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 definition is front-loaded: '[READ]' plus the core purpose lead, followed by parameters, grouping semantics, filtering rules, and result interpretation. It is dense and runs long, but nearly every clause (cadence threshold, occurrences weighting, milliunits) earns its place rather than repeating structured fields.

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?

An output schema exists, so return-value explanation is not required, and the description still helpfully interprets the key result fields. The gap is the two unexplained parameters (plan_id, since_date), which for a 3-parameter tool with 0% schema coverage leaves an agent unsure how to scope the query beyond the default window.

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 carries the full burden of parameter explanation. It defines 'months' well ('how far back to look, default 12'), but plan_id and since_date — which scope the query to a plan and a date bound — are never mentioned. Two of three parameters are left undocumented in both structured data and prose.

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 — 'Find repeating charges (subscriptions, memberships, regular bills) and estimate what each costs per year.' This is unambiguous and immediately distinct from siblings like analysis_overspent_history or analysis_copied_forward_months. An agent can route to this tool without opening the schema.

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?

Scope conditions are stated clearly: only outflows count, transfers between own accounts are excluded, and a series needs at least 3 charges on a recognizable cadence to be reported. This gives strong implicit guidance on when results will and won't appear. It does not name a sibling alternative or an explicit 'use this instead of X' rule, so it stops short of a 5.

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