Recurring charges

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and openWorld, so the safety profile is covered. The description adds genuinely new behavior: pagination is handled internally, overdue series are marked 'lapsed?', and results are restricted to the account owner — none of which the annotations convey.

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 core purpose is front-loaded in the first sentence, followed by output shape and constraints. Slightly terse shorthand ('lapsed?') costs a little clarity, but there is no wasted text.

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 values needn't be re-explained; the description covers what structured fields don't — internal pagination, the no-payment guarantee, and the owner-only disclosure rule. For a read-only detector with full schema coverage, an agent has everything needed to call and present it 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 description coverage is 100%, and every parameter (today, account, date_to, date_from, min_count, include_credits) is already documented in the schema, including the 'six to twelve months works well' hint and the quarterly/yearly min-count exception. The description adds no parameter-level meaning beyond that, so the baseline 3 applies.

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 — 'Read-only detection of subscriptions and other recurring charges' — which is clearly distinct from the sibling list/balance/transaction tools. It also names the underlying detector ('Same detector as `eb.py recurring`') and enumerates the derived outputs, so an agent knows exactly what this produces.

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?

Usage is implied rather than stated: the tool detects recurring series, so an agent infers raw transaction listing belongs to get_transactions, but no sibling is named and no explicit 'use this instead of X when Y' guidance is given. It does include one useful exclusion ('There is no payment action') and a handling rule ('Show the result only to the account owner'), which lifts it above pure absence of guidance.

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