delete_entities

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

Without annotations, the description discloses that deletion is irreversible and requires confirmation, which are crucial behavioral traits. It also implies a guarded execution by requiring filters, though it does not describe the exact deletion scope or potential side effects on dependent entities.

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 concise sentences: the first states the action, the second delivers the key safety requirement and prerequisite. No filler words; all information is actionable.

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 has 5 parameters and no annotations, the description covers the core safety constraints and purpose. However, it omits details on how filters combine (AND/OR), what the output schema returns, and whether it affects child entities. The presence of an output schema may cover return values, but the filter logic remains unspecified.

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 schema provides no parameter descriptions (0% coverage). The description compensates by stating that at least one filter is required and that confirm must be true, giving meaning to the confirm flag and the collective filter parameters. However, it does not explain the semantics of individual filters like type, block, layer, or handles.

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 opens with 'Borra entidades', clearly stating the tool deletes entities. This is a specific verb+resource that matches the tool name and distinguishes it from sibling tools like 'read_drawing' or 'transform_entities', none of which are delete operations.

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 explicitly instructs to 'create_working_copy' before using it and warns that 'esto no se deshace desde el agente' (this cannot be undone from the agent). It also requires 'al menos un filtro y confirm=true', providing clear conditions for use and an explicit prerequisite.

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