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

The description claims 'cria/atualiza/remove' while annotations declare destructiveHint=false, which contradicts the non-destructive hint. Although the production-data warning is valuable, the rule requires a score of 1 when the description contradicts 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?

The description is structured with a warning, usage notes, and a resource list, and it is not excessive in length. However, the broad 'cria/atualiza/remove' phrasing and the 'Flattened action' meta-note add confusion that reduces the value of the overall structure.

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?

It includes a production-data warning and enumerates writable resources, but it does not explain the account parameter, which resources are nested, what a patch body should contain, or return/error behavior. The missing action parameter and patch-vs-update ambiguity leave the description incomplete for safe invocation.

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?

The description adds meaning to body, id, parent_id, and bulk ids, but it instructs the agent to pass an 'action' parameter that does not exist in the input schema. With 0% schema coverage, this wrong instruction actively harms parameter understanding and outweighs the partial explanations.

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 domain (Bsoft TMS transport) and lists writable resources, and it ends with 'Flattened action: patch'. However, the opening line says 'cria/atualiza/remove', which obscures the actual patch-specific purpose and does little to distinguish this from the sibling update/delete tools.

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 provides useful conditions: update/patch/delete require id, nested resources require parent_id, and bulk mode accepts ids/parent_ids. It does not explicitly say when to choose patch over update/delete, so the when-to-use guidance is implied rather than explicit.

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