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

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=false), so the bar is lower; the description still adds real context: it creates a persistent, user-visible artifact in the Trading configs menu, and it explicitly disclaims live tracking and paper-trade side effects. It does not explain what happens when the same config is saved twice, which matters given idempotentHint=false.

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 core action, then scope, then alternatives, then Args – a logical order. Some redundancy: the live-tracking/paper-trade caveat is stated twice in adjacent paragraphs, costing a couple of lines in an already long description.

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 with no output schema, the description covers trigger conditions, side effects, supported kinds, and parameter meanings. The remaining gap is the return value – it never says whether the call returns a config id or label, which the agent needs to confirm success or reference the config later via list_my_trading_configs.

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%, so the description must carry the burden; it does define task_id's provenance ('returned by a prior start_* call') and adds a constraint the schema lacks for label ('max 100 chars'). Neither is fully illustrated (no example label, no statement of what happens if task_id refers to an unsupported kind).

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?

Specific verb + resource ('save the settings a run was started with as a trading config') with an explicit scope limit enumerated in the kinds list (backtest, walkforward, stochastic_backtest, basic_backtest, regime_optimization). It also names the sibling that handles scanners (save_workflow_result), so the agent can distinguish it without opening either schema.

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 an explicit when ('AFTER you've validated a config, e.g. walk-forward looked good'), an explicit when-not ('does not track the strategy live, starts no paper trade'), and names the alternative for the excluded case ('start_paper_trade does that'). Scanner kinds are routed to save_workflow_result, which is a genuine exclusion rule, not just a mention.

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