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

Annotations already declare readOnlyHint, openWorldHint and destructiveHint=false, and the description adds real context beyond them: what the response contains (numbers, BoQ rows with counting method, screening checks, official market figures, PDF link) and the notable constraint that DWG/DXF/IFC/Revit files are downloaded in Wai rather than returned here. It still says nothing about latency, cost, or failure behavior on ambiguous requests.

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?

Purpose and the domain list are front-loaded, and most sentences carry information an agent needs. However, it is a dense, over-stuffed block that repeats the return-contents list (quantities table, screening checks, link) across two sentences, and the asset taxonomy plus return inventory could be more scannably structured.

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 carries return-value explanation and does so thoroughly, alongside input examples and usage rules. Remaining gaps are minor — no guidance on ambiguous or unsupported requests, and no note on what the returned numbers' units or precision look like.

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; the description earns above that by explaining that lat/lng trigger an ISRIC SoilGrids ground screening and by giving concrete request formats ('154/33 kV substation 2x50 MVA', '20 MW solar farm with trackers'). This tells the agent how to phrase the free-text parameter far better than 'what to draw, with sizes' does.

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 ('draws an indicative site layout from a plain request') and immediately enumerates the asset classes it covers, which cleanly separates it from siblings like wai_design_building and wai_design_house. An agent can classify a request as in-scope without opening the schema.

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?

Gives an explicit trigger ('whenever the user asks to make / design / lay out a plant or project') and a negative rule (don't substitute web images of other projects, answer with returned numbers rather than a pre-call estimate). It does not name specific alternative siblings for adjacent cases, so it stops short of a full when-not/alternative map.

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