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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower, yet the description still adds real behavioral facts: stateless, nothing is persisted, missing values stay null and yield HOLD. These are non-obvious response-behavior traits not present in the annotations. It stops short of describing the actual returned payload shape.

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?

Three dense, front-loaded sentences with no filler; the core purpose leads and the CAL screen routing and HOLD rule follow. Domain codes are unexplained but are likely load-bearing for the target audience.

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 12-parameter tool with nested objects, no output schema, and zero schema description coverage, the description is thin: an agent cannot tell what belongs in pump/groundwater/evidence/geometry or what the HOLD output looks like beyond a status keyword.

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 0% across 12 parameters including nine nested objects (pump, drainage, groundwater, geometry, structure, evidence, constraints, investigation), and the description explains only the null/HOLD convention — no meaning is given for any domain-specific field, so it does not compensate for the schema gap.

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?

Specific verb+resource: 'Normalize a project brief into a stateless machine-readable engineering intake' clearly states the transformation and its stateless nature. It implicitly separates this from design/explain siblings (intake vs. design), but never names them, so the sibling differentiation is left to inference.

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 gives useful routing context — excavation/foundation groundwater projects map to CAL-065/066/067 screens — and states the HOLD rule for missing values. But there is no explicit when-to-use-this-vs-design_project guidance and no stated prerequisites or exclusions; usage is implied rather than directed.

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