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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and closed-world, so the safety profile is covered. The description adds genuine context beyond that: which CAL modules are actually executable (guarded) and that high-risk results are gated to human review, which tells the agent to expect partial automation. It does not disclose what 'versioned' means operationally (does a version get persisted?), which sits in tension with readOnlyHint and would matter to a caller.

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 short sentences with no filler, and the artifact statement is front-loaded. However, the second sentence is dense internal jargon (CAL-060/061, CAL-065/066/067) that consumes the middle of a very short description without explaining what those modules accept or produce. Efficient in length, but the space is spent on identifiers rather than on actionable meaning.

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 18 parameters, deep nested objects, no output schema, and 0% schema description coverage, this is a high-complexity tool whose description is far too thin. It never says what a successful call returns (a versioned design document? a module result set?) or what the required project_type values are, and no output schema exists to backfill that. The module and human-review notes are helpful but nowhere near sufficient for correct invocation.

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% across 18 parameters, so the description carries the full burden and largely fails it. The module list loosely maps to a few property names (tunnel, groundwater, drainage, structure, pump), but the required project_type, calculator_id, required_output, design_life_years, fluid_or_medium, and the eleven nested objects are given no meaning at all. An agent cannot tell what shape to send for geometry, constraints, or qa_qc from either the schema or the description.

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 first sentence ('Versioned preliminary engineering design') names the artifact produced but never uses a clear verb — it is unclear whether the call computes, stores, or versions a design. The second sentence enumerates which calculator modules are executable, which is useful domain detail but not a statement of what invoking the tool does for the caller. An agent can infer it is the design-generation entry point, but only by guessing against siblings like explain_design and project_intake.

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?

There is no explicit when-to-use guidance and no alternative is named, even though siblings (explain_design, project_intake, prepare_quote_request) plausibly overlap. The only usage-adjacent statement is the constraint that 'High-risk engineering remains human-review,' which indicates a boundary but not a selection rule. The agent is left to infer routing from the tool name alone.

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