drawing

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

Annotations only supply readOnlyHint=false, and the description goes well beyond that: it warns that create erases ALL entities, that save/save_as_dxf/plot_pdf will not overwrite existing files or QSAVE over the open drawing without a flag, and that a new 'YYMMDD - name' path is suggested instead. This is exactly the destructive-behavior disclosure an agent needs before invoking a write tool.

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 a one-line scope statement, then a scannable operation list, then a clearly headed safety block. It is long but nearly every line adds information; only the HP-specific flag names are opaque to a reader without context.

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?

With an output schema present, return values need not be explained, and the description covers all ten operations plus their destructive guardrails, which is sufficient for a multi-operation dispatcher. The only material omission is the undocumented include_screenshot parameter.

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% and the data object is untyped (additionalProperties), so the description carries the burden — it documents the per-operation data payloads ({name?}, {path}, {names: [...]}) and names the safety flags xac_nhan_xoa and ghi_de. The gap is include_screenshot, which appears in the schema but is never mentioned in the description.

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?

States the resource (drawing file management) and enumerates ten concrete operations with their verb semantics (create, open, save, purge, plot_pdf, etc.), so an agent can map an intent to an operation without opening the schema. The operation list also implicitly distinguishes it from siblings like entity/layer/block 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?

Gives explicit preconditions for the risky operations (create refused on non-empty drawing unless data.xac_nhan_xoa=true; save/export refused unless data.ghi_de=true) which is real usage guidance. However, it never routes the agent between this tool and the sibling tools (entity, layer, block, view), so the when-to-use-this-vs-alternatives question is only implied by the operation list.

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