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

With no annotations, the description carries the full burden and does real work: it declares the result 'unreviewed' and 'local', states that it requires evidence citations, and enumerates what it will not do (fill missing facts, authorize analysis, tax savings, payment or filing). What it omits is whether the call is side-effect free and what the response contains.

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?

Two tight clauses: the positive statement of what is computed comes first, then the guardrails. No filler, and the semicolon cleanly separates capability from restriction.

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 tool with a deeply nested draft object, no annotations and no output schema, the description leaves two gaps: it never indicates what a successful call returns (a projected result? components? flags?), and it points at a 'documented Development workbench contract' without any hint of where that contract lives. The negative guardrails are strong, but the positive shape of the interaction is thin.

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?

There is a single required nested 'draft' object and schema coverage is 100%, so the schema already documents the contract in detail. The description adds only the high-level constraints ('method-specific inputs', 'requires evidence citations', 'never invent cashflows, ownership, source citations or allocations'), which corroborate rather than extend 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?

The description pairs a concrete verb ('Calculate') with a clearly scoped resource ('an explicitly supplied unreviewed local what-if scenario') and signals it is a sandboxed projection rather than an authoritative audit, which separates it from the many audit_* siblings. It never names an actual alternative tool, and 'bound to current source components' / 'method-specific inputs' stay abstract about what is actually being modeled.

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?

Usage is only implied: the agent can infer this is for hypothetical scenarios built from user-supplied drafts rather than for filing, savings claims or formal analysis. There is no explicit 'use this when / use X instead' routing, and the natural neighbor get_property_model_readiness is never mentioned as a prerequisite.

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