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

Annotations only declare it is a non-read-only, non-destructive, idempotent operation. The description adds substantial behavior beyond that: out-of-range values are refused and never clamped, positions keep the simulation they were filled under, presets start from defaults as a clean slate, reading returns every field with range/default/effect, and an API key is required.

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?

The prose is long but front-loaded with the default posture before the field inventory, and each sentence carries a distinct concept (defaults, configurable surface, presets, read behavior, refusal policy, persistence, auth). For a 20-parameter engine, the length is defensible, though a couple of clauses could be tightened.

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 compensates fully: it explains what a read returns, what presets exist, that invalid values are refused rather than clamped, that existing positions retain their simulation, and that auth is needed. An agent has everything required to call this correctly.

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 20 parameters are already documented individually; baseline would be 3. The description adds value by grouping the fields by concern (book size, crossing cost, latency, fill behavior, refusals, fees/funding, liquidation), explaining preset semantics, and clarifying the read mode that the schema only hints at.

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 opens with a specific verb+resource: it configures the whole paper-trading simulation engine, and enumerates the exact knobs (margin, slippage, latency, partial fills, reject rate, fees, funding, liquidation). It is clearly the setter for simulation state, but it never names siblings such as paper_realism or paper_reset, so the sibling differentiation is left implicit.

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 clear context: pass a preset for the easiest route, omit every field to READ, and requires an API key. It also states a default posture (deliberately easy, good for learning, optimistic for proving a bot), which helps an agent decide when this is appropriate. It stops short of explicitly naming the alternative read tool or the reset tool.

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