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

Annotations already declare destructiveHint=true and idempotentHint=true, so the description's lower bar is met and it adds real context: capability validation warnings are returned on mismatch, OFF providers must not be probed, and a named setup page must be preserved. It does not, however, say what the previous provider setting becomes or acknowledge the destructive/overwrite nature itself.

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 purpose, but the rule block repeats itself ('Match the provider to the strategy's asset class requirements' appears twice) and contains an internal inconsistency: botspot_auto is listed as supporting options while a later section says it has no options data because Theta Data is off. Roughly 500 words for a two-parameter tool is heavier than needed.

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 2-param mutation tool with no output schema and no annotations covering selection logic, the provider routing, defaults, and OFF-provider handling are covered more than adequately. The remaining gap is customEnvVars, whose key/value semantics and required-vs-optional nature are never described.

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 0% and there is no enum, so the description carries the full burden. It effectively enumerates valid dataProvider values in quotes ('theta_data', 'alpaca', 'botspot_auto', 'custom', 'databento', 'polygon') plus per-provider asset classes, which the schema omits entirely. Only customEnvVars is left unexplained beyond a hint that 'custom' lets users supply their own data files.

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?

States a specific verb and resource: switching the active conversation's backtesting data provider. The scope ('active conversation') clearly separates it from start_backtest (runs a backtest) and set_strategy_requirements (declares requirements), so an agent can identify the right sibling without opening schemas.

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?

Gives per-asset-class defaults (stocks/indexes/crypto/futures → botspot_auto), explicit exceptions (options require alpaca or polygon), BYOK fallbacks, and a hard 'when not to use' rule (never select theta_data, never probe a provider declared OFF). Alternatives are named with the conditions that select them, leaving nothing to inference.

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