Scan the past 12 months of transactions to detect recurring payment patterns and generate subscription candidates. This operation can be slow on large transaction histories. Results are cached for 1 hour — subsequent calls within the cooldown return cached candidates. Check isFromCache in the response to know if the data is fresh. Requires finance:write scope (writes candidate records).
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does so well: it warns the operation 'can be slow on large transaction histories,' discloses a 1-hour result cache, tells the agent to read isFromCache for freshness, and states the required finance:write scope and its side effect (writes candidate records). This is exactly the behavioral context an agent needs before invoking a potentially expensive, mutating scan.
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?
Four tightly packed sentences, front-loaded with the core action, then performance, caching, and scope. Every sentence adds a distinct operational fact with no filler.
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?
No output schema exists, yet the description flags the isFromCache response field, and with no parameters and no annotations the remaining burden (performance, caching, auth, side effects) is fully covered. It could go slightly further on how results relate to the existing candidate list, but it is otherwise complete.
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?
The tool takes zero parameters, so the schema is empty and there is nothing to document. Baseline for a parameterless tool is 4; the description correctly adds no parameter noise.
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+resource: 'Scan the past 12 months of transactions to detect recurring payment patterns and generate subscription candidates.' This clearly distinguishes a detection/generation operation from the read-only sibling list_subscription_candidates. It does not explicitly name that sibling, so it falls just short of the top score.
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 caching note implies usage ('subsequent calls within the cooldown return cached candidates'), which tells the agent when calling again is worthwhile, but there is no explicit when-to-use versus list_subscription_candidates or create_subscription, and no stated prerequisites beyond the scope requirement.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.