vpp_edit_class_model

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

With zero annotations the description carries the full burden, and it does substantial work: non-destructive output-to-new-file, atomic transaction semantics, sequential ordering, conditional refusal on remove_member, ID preservation in change_operation keeping sequence-diagram messages valid, and side effects for move_class (relation lines recomputed) and fit_class (box resized). Remaining gaps are the source_path/output_path/overwrite_output behaviors and error/partial-failure reporting, but the mutation surface is well disclosed.

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?

Front-loaded with purpose and a one-line atomicity rule, then a dense bullet-per-operation reference rather than prose. It is long, but nearly every line encodes syntax an agent could not otherwise infer (op names, field names, override semantics); the closing type and visibility glosses are worth their space.

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?

For a multi-op mutation tool with an output schema, the description covers the operation vocabulary, ordering, atomicity, and key side effects well. It stops short of describing the source_path contract, overwrite_output behavior, or what a rejected batch reports back, which an agent would want before a first call.

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 description coverage is 0%, so the description must compensate, and it does so heavily for the dominant parameter: every 'op' variant is enumerated with field-level meaning, direction conventions for generalization/realization/dependency/aggregation, allowed type names, and visibility syntax. The three path/overwrite parameters are only implicitly addressed ('wynik do NOWEGO pliku') and overwrite_output is never explained.

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 pair ('Zmiany w modelu klas i na diagramie klas') and immediately adds the key distinguishing scope: the result goes to a NEW file with the original untouched. This clearly separates it from read-only siblings like vpp_get_class and vpp_list_classes without needing to name them.

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?

Gives strong operational context: changes are applied in order and are all-or-nothing, and remove_member refuses when a message still calls the method. What it lacks is any explicit routing versus alternatives (e.g., when to use change_operation vs remove_member+add_operation), leaving that to inference from the genre of the tool.

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