ass_get_drawing

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

With no annotations, the description carries the full burden, and it does disclose non-obvious behavior: the returned commands, bbox, size, centre and path length are all in scale space (units as written in the file), with the explicit conversion factor 2 ** (1 - scale). It stops short of stating read-only/side-effect status explicitly, relying on 'Inspect' to imply it.

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 the two input modes, then the scale caveat, then the return shape; the bulleted structure is easy to scan. The enumeration of every return dict key is somewhat verbose given an output schema exists, which keeps it from a 5.

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 read-only inspection tool with three optional params and an output schema present, the description covers everything an agent needs: modality selection, the scale-space semantics that would otherwise cause silent unit errors, and the aliasing of center/centre. Return values are additionally backed by the output schema.

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 schema only gives bare titles, so the description must compensate — and it does. It defines exactly what index + doc_id mean (line at that 0-based index in doc.events() order, split with tags.drawing_parts) and what text accepts (a full override line containing '{' or a \p tag, or bare drawing path data), plus the 'exactly one' constraint.

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?

Specific verb ('inspect') plus resource ('drawing part of a line, or a raw drawing string') that clearly identifies it as a read/extract operation on drawing data. It does not, however, name or differentiate itself from close siblings such as ass_drawing_info, ass_drawing_bbox or ass_drawing_to_svg, so an agent must still infer the boundary.

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 mutual-exclusion rule for the two input modes (index+doc_id vs text) is spelled out clearly, which is real usage guidance. But there is no when-to-use / when-not-to-use framing relative to alternatives (e.g. ass_get_line, ass_drawing_info), so selection among siblings is only implied.

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