recurring_expenses_report

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

Annotations already declare readOnlyHint=true, so the safety profile is covered; the description then adds real behavioral substance: the minimum-3-invoice regularity rule, the cadence categories detected, and that it flags increases above threshold and invoices that were expected but never arrived. It stops short of noting limits such as lookback bounds (the schema's 3-60 range is not echoed) or how sparse data is handled.

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?

A single dense but front-loaded passage that first states the resource and lookback window, then the inclusion criteria, then the returned fields, then the alerting behavior. Every clause carries information; the only cost is that it is one long sentence with no visual separation between scope, criteria and outputs.

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, the description does the necessary work by enumerating the return fields (average amount, last date, next expected date, estimated annual total) and both alert types. Combined with the read-only annotation and simple three-parameter surface, an agent can call this confidently; only explicit lookback bounds and empty-result behavior are missing.

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 coverage is 67%, and company_id and increase_threshold_pct already carry descriptions. The description adds meaning for the undocumented 'months' parameter (the lookback window for scanning received documents) and reinforces what the threshold triggers, but it adds nothing for company_id scope and no format guidance. With most parameters documented in-schema, this is adequate rather than compensating.

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 names a concrete analysis (recurring expenses from received documents) and pins down the detection rule (suppliers with at least 3 invoices at a regular cadence) plus the exact figures returned. That is far more specific than the name alone. It does not explicitly contrast itself with near-analytics siblings such as cashflow_forecast or receivables_report, which keeps it from a 5.

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 only implied: an agent can infer this is the tool for spotting recurring supplier costs and price increases over a lookback window. There is no explicit when-to-use/when-not statement and no named alternative, so routing between it and the other report tools is left to inference.

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