Zovo Floor Plan

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

Annotations already declare readOnlyHint=true, idempotentHint=true, openWorldHint=false, and destructiveHint=false, so the safety profile is covered. The description adds valuable behavior: exactly what the returned area table, covered area, and problem list contain, including overlap area and wall-run-past-end cases. It does not describe auth or rate limits, but those are not relevant here.

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-loads the use case, then the input relationship, then outputs and exclusions. Every sentence adds distinct value despite the dense single paragraph.

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?

Complete for a complex read-only validation tool. It covers inputs by reference to make_floor_plan, summarizes the output schema's key results, and clearly bounds what it does not check.

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 input schema already documents rooms, doors, windows, units, and title thoroughly. The description adds only the useful relationship that it takes the same rooms, doors, and windows as make_floor_plan, without adding parameter-specific syntax or semantics beyond 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?

States a specific verb and resource: check a floor plan. It names the sibling make_floor_plan and clarifies this tool validates rather than draws, so an agent can distinguish it from drawing the plan.

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?

Explicitly says when to use it: before drawing a plan, or to diagnose a refusal, with concrete example questions. It also states when not to use it for drawing or code compliance, routing the agent to the sibling make_floor_plan.

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

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

Annotations already establish a read-only, idempotent, closed-world operation, and the description adds substantial context on top: it discloses the outputs produced (areas, interactive plan, SVG/PDF/CSV), error behavior (refuses overlapping rooms and openings past a wall end, naming them), and explicit capability limits (no curved walls, stairs, furniture, wall thickness, no image/file input).

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?

A single dense paragraph that is front-loaded with the trigger and examples, then capabilities, then return values, then refusals and limitations. Each sentence carries distinct information with no filler.

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 complex 8-parameter generation tool, the description covers inputs at a high level, the outputs (even though an output schema exists), failure modes, and scope boundaries. An agent has everything needed to decide to call it and to construct a plausible argument set.

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 every parameter is already documented in detail, and the description largely restates that (width east-west, length north-south, x/y vs right_of/below/left_of/above, doors/windows by wall and offset, scale forms). It confirms the intended mental model but adds little syntax or constraint detail beyond the schema, so baseline 3 applies.

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?

States a specific verb and artifact ("draw a floor plan to scale from room sizes") with two concrete example utterances, and the surrounding text makes clear this is a generation tool rather than a validator, distinguishing it from check_floor_plan without naming it.

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?

Opening clause "Use this when the user wants a floor plan, room layout or apartment plan" plus sample phrasings gives a clear trigger condition. It never names the sibling check_floor_plan or states when-not to use this, so the routing guidance stops short of explicit alternatives.

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