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

With no annotations provided, the description carries the behavioral disclosure burden. It explains that the tool reviews from a building-code perspective, points out violations, and guarantees that violation items are not omitted from the answer. It also clarifies that input must be parsed structural data, not an image, which is key behavioral context.

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?

Four short, front-loaded sentences each earn their place: purpose, trigger condition, input format, and output guarantee. There is no redundancy or filler, and the key perspective 'building-code review' appears immediately.

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?

Given that an output schema exists and the input schema already documents all six parameters, the description provides everything needed for selection and invocation: when to use it, what to feed it, and what behavior to expect. Optional parameters like jurisdiction and site_scope are covered by the schema, so no additional description burden is required.

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 coverage is 100%, so the baseline is 3, but the description adds meaning beyond the schema by explaining that inputs should be the structure read from the drawing—rooms with use and external-window presence, adjacency, openings, and circulation. This helps the agent construct valid parameter values instead of passing a raw image.

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: reviewing floor plans and layouts from a building-code perspective and flagging violations of daylight, ventilation, egress, and area requirements. This clearly distinguishes it from sibling tools like compare, path_between, or scenario, which serve different analytical purposes.

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?

It explicitly says to use this tool when the user shares drawings or requests spatial-composition review. It does not name alternative tools or give when-not-to-use exclusions, but the trigger conditions are clear enough for an agent to select it appropriately.

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