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

Annotations already cover the safety profile (readOnly, non-destructive), and the description adds substantive behavior the annotations cannot: the v1-to-v2 read mapping, the meaning of interview_due/status states, guardrail_conflicts semantics, and the important disclosure that the scan schedule is never persisted to Moby and must be recreated agent-side each session.

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 highest-priority instruction and the connect-time requirement, then organized as scannable bullets tied to specific response fields. It is long and embeds an entire onboarding workflow script, which is more than a tool description strictly needs, but nearly every line carries operational meaning.

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?

An output schema exists, so return values need not be restated, yet the description still annotates the semantically tricky fields (interview_due, status, recommended_strategies, guardrail_conflicts). For a zero-param read tool plus a multi-step onboarding flow, an agent has everything needed to call it and act on the result.

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?

With zero input parameters the baseline is 4, and the description adds real value by explaining why: 'The wallet is never a parameter. This returns the CURRENT USER's own data, resolved from their API key' and that querying another wallet is impossible. That closes a common misuse path, though there is no parameter surface to describe.

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 plus the exact payload returned (experience, assets, work mode, sizing, protection) and even notes v1 rows are normalized to v2. It also draws an explicit boundary against get_my_guardrails by explaining that the profile is intent while guardrails are enforcement.

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 unconditional when rule ('call this BEFORE ANY OTHER TOOL on every connect — before balances, portfolio, strategies or research') and enumerates the branch conditions for each `status` value, including the explicit exclusion 'skipped = ... do not ask again unless interview_due is true'. Alternatives and hand-offs (get_my_guardrails, list_strategies, save_trading_profile) are named.

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