spending_by_category

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

With no annotations supplied, the description carries the full burden and does well: it discloses that transfers and report-excluded transactions are dropped, that an (Uncategorized) bucket is preserved, and that accounts default to checking plus credit-card. It omits any statement of read-only safety or of the shape of the aggregation result, which keeps it from a 5.

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 sentence with zero filler, front-loading the core action and following with the qualifying rules in order of importance. Every clause conveys a distinct behavioral fact.

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?

For a five-parameter read aggregation with no annotations, the description covers the exclusion rules, default account scope, and date semantics that an agent needs to call it correctly. It stops short of describing what the aggregation returns (totals, grouping keys) and leaves the group_by enum undocumented, but no output schema exists to clarify that.

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 only 40%, so the description must compensate, and it does meaningfully: 'inclusive date range' clarifies start_date/end_date boundary semantics, and 'defaults to checking + credit-card accounts' explains account_types behavior when omitted. The group_by enum (category vs parent_category) and account_names filtering receive no explanation in either place.

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: 'Aggregate consumer spending (negative splits) by category' with an inclusive date range. An agent can distinguish this category-based aggregation from a time-series sibling like spending_over_time, though the description never names or contrasts any alternative explicitly.

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: the category framing and date range suggest when to reach for it, and the account default hints at scope, but there is no explicit when-to-use, when-not-to-use, or pointer to a sibling tool for other cuts of spending data.

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