build_drawing

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

With no annotations, the description carries the behavioral burden. It usefully says the drawing is 'Saved to path when given' and that it returns what was made plus problems found by check_drawing, but it does not disclose overwrite behavior, side effects, or permission requirements for a mutating build operation.

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 purpose is front-loaded, followed by the necessary spec shape and then the save/return behavior. The large spec block is dense but justified for a complex nested parameter, and there is little wasted prose.

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?

The description gives enough to construct a rough spec and understand that the result includes check_drawing problems, which is important because no output schema exists. However, for a complex mutating tool with no annotations and low schema coverage, it omits important operational details such as overwrite behavior, validation errors, and routing relative to sibling drawing tools.

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 input schema only defines spec as a generic object, so the description must compensate. The inline spec example is quite detailed, covering part, sheet, scale, views, import, dims, callouts, symbols, notes, tables, props, and layout, which substantially clarifies the nested object; it is still an example rather than exhaustive documentation.

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 states a specific verb and resource: build a drawing from a spec, then edit the spec and rebuild. It clearly frames the tool as a spec-driven drawing builder rather than incremental feature creation, though it does not explicitly distinguish itself from the similar sibling make_drawing.

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 implies usage through phrases like 'from scratch' and 'edit the spec and rebuild to fine-tune', giving a reasonable workflow context. However, it does not state when to prefer this over make_drawing, add_view, or edit_view, nor does it give exclusions.

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