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

Beyond annotations (readOnlyHint, idempotentHint, destructiveHint), description adds key behavioral traits: it is date-specific, grouped by product type, paginated, and includes specific fields like ISIN and institution. This provides useful context not in annotations.

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?

Single sentence conveys essential information efficiently, front-loading key components. However, it could be slightly restructured for clarity, e.g., listing parameters separately.

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?

The description covers returned fields, grouping, and pagination, which is adequate for a read-only tool with annotations. However, it lacks explanation of parameters and return format (especially since no output schema exists), leaving some gaps in understanding.

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 has 0% description coverage and no enums or required fields. The description vaguely hints that 'data' is a date and 'pagina' is for pagination, but does not explicitly describe each parameter's format, constraints, or how they relate to the output. More parameter guidance is needed.

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?

Description clearly states it returns detailed position by asset on a specific date, listing specific fields (ticker, quantity, close price, etc.) and is grouped by product type and paginated. This distinguishes it from siblings like b3_get_carteira or b3_get_patrimonio which provide different views.

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 implies usage for retrieving per-asset position details on a given date, but does not explicitly state when to use this tool versus alternatives like b3_get_carteira or search tools, nor does it mention when not to use it.

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