prepare_drawing

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

Annotations declare readOnlyHint=true, so the description doesn't need to justify safety. It adds value by disclosing that the tool saves files (overview and crops) as part of its operation, and it explicitly enumerates what it does not do (no view labelling, no CAD feature recognition, no dimension inference). This goes beyond the annotation and gives the agent an accurate mental model of its capabilities and boundaries.

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 dense but well organised: purpose first, then capability, then limitations, then usage, then parameter details. Every sentence adds value; there is no fluff. It is longer than a one-liner, but the complexity of the tool justifies it. The negative-capability list is particularly useful and is not redundant.

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?

An output schema exists, so return format is defined elsewhere. The description covers usage, parameter semantics, limitations, and the intended workflow. It doesn't mention error cases or what happens if the input is not a valid drawing, but for an inspection-prep tool this is acceptable. The description is sufficient for an agent to call it correctly in a typical workflow.

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 full burden. It explains each parameter: image_path with accepted formats and read-root constraint, output_dir with write-root constraint, max_regions with range 1..30, and padding with pixel range 0..500. This is exactly the kind of semantic enrichment that makes the tool callable without opening the schema.

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 ('prepare') and resource ('raster engineering drawing'), then details the exact behavior: detecting spatial regions, saving an overview and crops, and returning bounding boxes and paths. It also explicitly lists what the tool does NOT do (label views, recognise CAD features, interpret lines, etc.), which strongly distinguishes it from siblings like crop_drawing, render_drawing, and recognise_features.

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 gives explicit usage guidance: 'Use it once near the start instead of repeatedly writing shell/PIL crop scripts; inspect the returned overview and only the relevant crops.' It also tells the agent to treat printed dimensions as authoritative, which is a clear directive on when to rely on the tool and when to defer to original data. This is more than enough to guide correct usage.

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