subscription_audit_report

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

No annotations are provided, so the description carries full burden. It details each output section (tracked, expected_missing, candidate_new) and discloses that candidate_new is advisory. It does not mention any destructive behavior, which is fine for a report. Slight room for improvement: clarifying that it is read-only.

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 description is somewhat lengthy but well-structured: first sentence states purpose, then parameter details, then output breakdown. Every sentence adds value, but it could be slightly more concise without losing clarity.

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?

Given the output schema exists (though not shown in full), the description explains return values in detail: tracked is full roster, expected_missing is deterministic alert, candidate_new is advisory. All parameters (0 required) are covered, and the tool's behavior is fully described. No gaps for this report-type tool.

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 must compensate. It explains end (defaults to today), start (defaults to a year back), and min_occurrences in context. However, 'day_tolerance' is not mentioned, leaving one parameter unexplained. The YYYY-MM-DD format is given, adding value.

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 clearly states the tool's purpose: to flag tracked bills that didn't post and surface untracked recurring merchants as candidates for judgment. The verb 'flag' and 'surface' with specific resources (tracked bills, untracked merchants) distinguish this from siblings like subscriptions_detect.

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 guidelines are provided: explanations of date defaults, min_occurrences, and the advisory nature of candidate_new. The description tells the assistant to decide real subscriptions from candidates. However, it doesn't explicitly state when not to use the tool vs alternatives.

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