Get Recurring Streams

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

Beyond readOnlyHint/openWorldHint, the description discloses the compact output shape, the verbose alternative, and the important caveat that forecasts are expectations rather than posted transactions. It stops short of stating row ordering, pagination, or count limits, but the honesty about forecast semantics is real added value.

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?

Front-loaded purpose sentence, then a tidy Args block, then output notes. The long enumeration of compact-row fields is somewhat redundant given an output schema exists, but it earns partial keep by anchoring the merchant.id/merchant.name pointer.

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 three optional booleans, annotations, and an output schema, the description covers purpose, knob behavior, output distinction, and a follow-up tool. The one meaningful omission is sibling differentiation versus get_recurring_transactions, which matters for tool selection in a large toolset.

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 has to carry parameter meaning, and it does explain all three flags in behavioral terms (skips paused streams, adds credit-report liability streams, returns full upstream objects). It omits the defaults that the schema defines (active_only and include_liabilities default to true), which is a small gap for a reader who only sees the 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?

States a specific verb and resource ('List every recurring stream (merchant schedule) with its next forecast'), which is concrete and scoped. It does not distinguish itself from the sibling get_recurring_transactions, so an agent has to infer the difference between 'streams' and 'recurring transactions'.

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 through argument semantics (active_only skips paused, include_liabilities pulls in loans/cards, verbose returns full upstream objects) and a downstream pointer ('merchant.id and merchant.name feed update_recurring_transaction'). There is no explicit statement of when to pick this over get_recurring_transactions or when not to use it.

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