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

Annotations already declare read-only, idempotent, non-destructive, so the safety profile is covered; the description goes further by disclosing the detection algorithm's tolerance (steady interval across five frequencies), the default window and its 13-month caveat for yearly charges, and the `warnings` array with per-bank messages and a conditional `reconnect_url`. That reconnect hint is meaningful behavioral context an agent would otherwise discover only at runtime.

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?

Three sentences, front-loaded with the purpose and algorithm before defaults and the warnings detail. The final warnings sentence is dense but each clause carries operational value; only the prose is slightly heavier than necessary.

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 no output schema, the description takes on the job of explaining return fields (typical amount, frequency, last charge date, total) and the warnings payload, which it does. Combined with the 100%-covered schema and read-only annotations, an agent has everything needed to call this correctly.

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%, so the baseline is 3, but the description adds real semantics beyond the schema: it explains that the window must span 13+ months for yearly detection, which no individual parameter description states. It does not explain how min_occurrences interacts with interval detection, leaving one gap.

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?

States a specific verb and resource (find recurring charges) and describes the actual detection method — grouping per merchant and identifying a steady weekly/biweekly/monthly/quarterly/yearly interval. This is functionally distinct from siblings like get_merchant_history or get_monthly_cashflow, so an agent can select it 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?

Gives clear operative guidance for the date window: default is 6 months and yearly charges require 13 months or more, which is exactly the kind of constraint an agent needs to pass correct arguments. It stops short of naming alternatives (e.g. get_merchant_history for single-merchant lookups), so there are no explicit exclusions or sibling routing.

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