Drawing Legibility

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

The annotations already mark the tool as read-only, so the description adds substantial behavioral value beyond them. It discloses the exact return envelope ({ok, violations, labels, segments, views}), the violation codes (overlap/crosses_view/out_of_border), the meaning of ok=True, the effect of min_gap, and that inspection balloons are also checked. This gives an agent a reliable model of behavior with no contradiction to the read-only annotation.

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 description is front-loaded with the core purpose and violation examples, then layers in parameter semantics, return-value semantics, and an edge case about inspection balloons. Every sentence contributes new information, and there is no filler, tautology, or repetition of the title or annotations.

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 no output schema, the description adequately explains the return structure, the meaning of ok, and how violations are reported with codes and reasons. It does not explain what labels, segments, and views contain, nor how to obtain the page handle, but those details are secondary to invoking the check and interpreting its pass/fail result. The description is sufficient for a typical 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 carries the burden of explaining parameters. It does explain min_gap well: 'breathing room required between two labels' in millimeters. However, it never defines the required page parameter beyond the general notion of a 'drawing page,' leaving its format, source, or relationship to other drawing tools undocumented. The partial compensation is useful but incomplete.

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: it 'flags' legibility problems on a drawing page's 'ACTUAL placed graphics.' It enumerates concrete violation classes — overlapping dimension labels, dimension lines crossing unreferenced views, and items past the sheet border — which makes the tool's purpose precise and distinguishable from generic drawing checks such as drawing_gate.

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 when to use the tool: as a legibility gate after graphics are placed, checking whether placed dimensions and balloons read cleanly on the sheet. It does not explicitly state when not to use it, nor does it name an alternative for broader drawing validation, so the usage context is clear but the exclusion/alternative guidance is left implicit.

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