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

Annotations already establish readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds that the tool aggregates and groups transactions, which is useful, but it does not disclose behavioral details such as result limits, default grouping when groupBy is unspecified, or how timeBucket affects output. With annotations covering the key risk traits, this is acceptable but not rich.

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 a single, compact sentence with no filler words. It front-loads the core action and outcome. While it lacks structured sections, it is appropriately sized for a read-only summary tool; a slightly longer description with usage context would be more helpful, but there is no unnecessary prose.

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 tool's complex filter schema cum 5 top-level parameters, an output schema, and many sibling aggregation tools, this description is too sparse. It does not explain when to use it, what the filter constraints are, how grouping dimensions work, or what the output structure covers (despite output schema existing). An agent would struggle to correctly invoke this without diving into the schema and guessing about intended use.

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 only 20%, so the description must compensate, but it barely does. The only parameter hint is 'by a given dimension' vaguely mapping to groupBy. There is no explanation of the required 'filter' object, the meaning of scope, fieldId, or timeBucket. The description adds minimal value beyond the schema's own sparse annotations.

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 uses a specific verb ('Aggregate'), a clear resource ('transactions'), and an explicit outcome ('P&L groups (income/expenses)'), making it immediately distinguishable from single-transaction getters (transaction_get_transaction) and raw list tools (read_transactions). The phrase 'by a given dimension' correctly points to the groupBy parameter, reinforcing the aggregation intent.

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 description provides no guidance on when to use this tool versus alternatives like accounting_get_profit_and_loss or cap_table_get_transaction_summary. There is no mention of preferred use cases, exclusions, or conditions that would select this tool over siblings, leaving the agent to infer from names alone.

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