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

The readOnlyHint=true annotation covers the safety profile, so the description's silence there is tolerable. Beyond that it adds nothing: no statement of what the returned series looks like, whether unnamed series are dropped, what happens on invalid series references, or that the response is a computed series spec rather than persisted state.

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 definition is short with no filler or redundancy, which is good, but two sentences for a schema this elaborate is under-specification rather than concision. Nothing is front-loaded beyond a bare purpose clause.

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?

This is the most complex kind of input schema (deep nesting, many polymorphic ops, no property descriptions at all) and there is no output schema, so the description carries full burden. Two sentences do not begin to explain the required structure, the version const of 2, the relationship between series ids and signal/position inputs, or what a valid call looks 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 description coverage is 0% and the schema is a deep nested structure with dozens of op variants inside series (price, observations, session, lag, smooth, rank, ratchet, pivot) plus signals, simulation and money. The description names three fields at the top level, omits the required `run` wrapper and all of money/signals/simulation, and adds no meaning beyond the key names themselves - leaving essentially the entire parameter surface undocumented.

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 gives a verb and object ("Build named time series") and a vague source ("a run form"), so the agent knows roughly what it produces. But it never mentions that the same request can also define signals, simulation/positions, money and capital settings, nor does it differentiate it from siblings like build_signal or simulate. The purpose is only partially surfaced for what the schema shows.

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?

"Needs version, data, and series" is the only usage-adjacent statement and it is partly wrong: the schema requires run.version and run.data, while series defaults to an empty array and is optional, and the required `run` wrapper itself is never mentioned. There is no when-to-use, when-not-to-use, or alternative-tool guidance versus build_signal or simulate.

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