get_balances

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds one genuinely useful behavioral point — that as_of reflects the data state while received_at is merely retrieval time — but says nothing about aggregation granularity, sign conventions, or what a partial result looks like.

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?

Two short sentences with no padding, which is appropriately sized. But the terse noun-phrase opening and the unexplained reference to as_of/received_at (fields absent from the schema) make it cryptic rather than efficient — the front-loaded sentence costs the reader a second pass.

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 tool with one required argument, no output schema, and no annotations covering semantics, the description should at minimum document the months format and the shape of the returned balance breakdown. It leaves both open and instead introduces temporal concepts the agent cannot map to any input field.

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 0% and the sole required parameter, months, is never explained — no format ("YYYY-MM" vs month names), no range behavior, no ordering. Worse, the description spends its only parameter-adjacent sentence on as_of and received_at, which do not appear in the schema at all, leaving the real parameter undocumented in both places.

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 identifies the resource and its breakdown ("Opening/movement/closing balances"), which tells an agent what kind of financial data comes back. However, it supplies no verb and no differentiation from siblings such as get_pnl or get_cashflow, so the agent must infer the distinction from names alone.

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?

There is no statement of when to use this tool versus get_pnl, get_cashflow, or list_months, and no prerequisites such as month-close state. The as_of/received_at note hints at data-state semantics but never frames it as a selection criterion between tools.

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