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

With no annotations, the description must carry the behavioral load. It discloses that it is a GET (implying read-only), that company must be explicit, and that the response is fixed JSON, which is meaningful. However it omits behavior beyond that, and the 'fixed JSON' phrasing only loosely conveys the return shape already covered by the output schema.

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?

Terse, front-loaded, and fragment-style with no wasted words; the required fields and endpoint come early. Lean almost to a fault, but nothing redundant.

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?

An output schema exists so return values needn't be explained, and required filters are listed. But the query object is undocumented in schema and only partially covered by the description, and the fuller filter set is outsourced, so an agent may need a second tool to call this correctly.

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 0% and the query object is opaque (additionalProperties: true), so the description is doing real work by naming required query fields dateFrom, dateTo, accountNumber. It also clarifies company_name must be supplied explicitly. It still defers the full filter vocabulary to describe_nextesy_operation, leaving gaps.

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+resource (get account-balance report) and names the underlying GET endpoint. An agent can tell it retrieves an account balance report, but it never explicitly contrasts with close siblings like get_balance_sheet or get_account_statement_entries, so differentiation is left to inference.

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?

It routes the agent to describe_nextesy_operation for the filter set, which is a useful pointer, but gives no guidance on when to choose this report over the other reporting siblings. Usage is implied rather than stated.

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