mdpa_add_entities

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

No annotations, so the description carries the full burden. It does disclose two genuinely non-obvious behaviors: property_id defaults to 1 and is invalid for geometries, and using sub_model_part silently adds the new entities and their nodes to that part plus all ancestors. It omits write-side behavior the agent needs: what happens to an existing file, what 'overwrite' toggles, and what errors occur on bad node ids.

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?

Four dense sentences with no filler; the kind enumeration is front-loaded and each subsequent sentence adds distinct information (entity_type naming, entity item shape, sub_model_part semantics). Slightly cramped, but nothing is 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 need no explanation, and the description covers the core modeling semantics needed to construct a call. The gap is the required 'path' and the 'output'/'overwrite' file-handling parameters, which an agent must infer from bare schema property names.

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%, so the description must compensate, and it largely does: it defines the kind vocabulary, explains the entity_type naming convention and its node-count suffix, and spells out the exact per-item shape of 'entities' ([{nodes, id?, property_id?}]) plus the sub_model_part effect. It leaves three parameters undocumented – notably the required 'path' plus 'output' and 'overwrite'.

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?

Opens with a specific verb+resource: 'Add elements, conditions or geometries of one type,' immediately enumerating the three modeling object classes and clarifying the union-per-call constraint. This cleanly separates it from siblings like mdpa_add_nodes (nodes only) and mdpa_get_entities (read side) without needing the schema.

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?

Usage is strong on mechanics – it tells you the meaning of 'kind', how the entity_type suffix fixes node counts, and what sub_model_part does – but never states when to pick this over alternatives such as mdpa_set_entity_properties, mdpa_merge, or mdpa_get_entities, nor does it name any prerequisite (a valid path, existing node ids) or exclusion.

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