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

Goes well beyond readOnlyHint/openWorldHint: it explains the candle-sourcing behavior (fetched from the venue when candles[] is omitted, cached for past sessions, network-free and reproducible when supplied), and states a hard prerequisite that session_date be a completed UTC session before today, plus the failure mode (error when no candles). These are exactly the operational details an agent needs before calling.

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?

Front-loaded with the tool's identity and the guiding question, then a compact returns inventory and sourcing caveats. It is dense and on the long side, and the label enumeration partly duplicates the returns list, but nearly every clause carries information.

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 by enumerating the return fields (structure, description, bias, key_signals, key_levels, tails, scenario_framing, invalidation) so the agent knows what it gets. Combined with the data-sourcing and date-precondition notes, nothing material is missing for a 7-parameter analytic tool.

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 schema already documents every parameter, including enums, defaults and the YYYY-MM-DD format. The description reinforces the candles[]/prev_candles omission trade-off and the session_date constraint, but adds little syntax or semantics the schema doesn't already carry — baseline 3 applies.

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?

Names a specific analytic output (day-type classifier) and enumerates the label set (trend/balance/neutral_trend/normal/normal_var) plus the inputs it derives from (TPO, initial balance, range extension, value migration). This is clearly distinguishable from neighbors like run_value_migration or run_breakout_acceptance, which cover only sub-components.

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?

Provides an explicit trigger question ('is this a trend day or a balance day?'), which gives the agent a clear use context. However, it never names an alternative tool or a when-not condition, even though sibling tools such as run_value_migration overlap on the value-migration input.

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