Aggregate Transactions

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description only needs to add context beyond safety. It does: warns 'never sum across currencies yourself' and states the default scope ('all your completed statements'). These are meaningful behavioral constraints. It does not describe edge cases like empty results, but given the annotation coverage, this is sufficient.

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 sentences with zero filler. The purpose is front-loaded, followed by the critical per-currency warning and default scope, then the pointer to get_credits. Every sentence earns its place; nothing is redundant or excessive.

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?

There is no output schema, so the description should clarify what the tool returns. It notes results are per-currency, implying multiple currencies may yield multiple results, but doesn't explicitly state the return shape (e.g., a list of {currency, value}). It covers default scope and how to narrow, and the schema richly documents parameters. The only minor gap is the exact output format, which keeps it from a 5.

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 100%, with detailed descriptions for scope, filter, and metric. The description adds only a small reinforcement ('pass scope to narrow') that is already implied in the schema's scope description. It does not add new meaning beyond what the schema provides, so the baseline of 3 is appropriate.

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 ('Compute'), a clear resource ('transactions'), and enumerates the metric types (sum/average/count/max/min). It explicitly distinguishes from get_credits by saying that is not a transaction, and the phrase 'single metric' differentiates from grouped aggregation siblings like group_by. The purpose is unmistakable.

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?

Provides explicit guidance on when to use scope (to narrow by accounts/products/date range) and clearly points to get_credits as the alternative for quota/credits questions. It does not mention when to prefer group_by, top_n, compare, or time_series, but the 'single metric' phrasing implies those are for multi-metric or grouped output. That gap keeps it from a 5.

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