Recurring List Recurring Streams

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

Annotations already carry the safety profile (readOnlyHint=true, idempotentHint=true, openWorldHint=true, destructiveHint=false), so the bar for added context is lower but the description still must add value. It adds none: no mention of the include_pending/include_liabilities defaults, no filter behavior, no output-shape semantics. The description contributes zero behavioral context beyond the structured annotations.

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 words is under-specification, not conciseness. There is no wasted text, but the description is far smaller than the tool's complexity warrants (5 parameters, a nested filter object, three output modes). A single tautological sentence cannot serve as an adequate definition.

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 and a one-line description, an agent cannot anticipate what the summary/full/raw output modes return, what include_pending and include_liabilities control, or how filters compose. The description does not distinguish this tool from the recurring get/summary/occurrences siblings. For a 5-parameter list tool, this is materially incomplete.

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 only 40% (only fields and output_mode have schema descriptions; filters, include_pending, and include_liabilities do not), so the description must compensate for five parameters. It mentions none of them, leaving ambiguous terms like 'pending' and 'liabilities' unexplained. The nested RecurringFilterInput properties are understandable only through naming inference and the enum values already present in the schema.

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 'List recurring streams.' is a near-verbatim restatement of the tool's own title ('List Recurring Streams') and name (recurring_list_recurring_streams). It supplies no definition of what a recurring stream is and does not differentiate the plural list operation from siblings like recurring_get_recurring_stream or recurring_get_recurring_summary. This is a tautology rather than an informative purpose statement.

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 gives no guidance on when to call this tool versus recurring_get_recurring_stream, recurring_list_recurring_occurrences, or recurring_get_recurring_summary. There is no mention of filter-driven selection, default inclusion of pending/liability streams, or when the summary/full/raw output modes are appropriate. An agent must infer all selection context from the tool name alone.

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