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

Goes well beyond the readOnly/non-destructive annotations by disclosing privacy boundaries (never returns SSNs, identity documents, provider credentials, or KYC payloads), the membership roles required to receive a handoff URL (owner/founder/cofounder/operator), a sandbox-vs-production warning, idempotency, and canonical read semantics. These are substantive behavioral facts an agent could not infer from the annotations.

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?

Purpose and privacy boundaries are front-loaded, which is good, but the labeled-section format (Canonicality/Idempotency/Confirmation boundary) is verbose. The confirmation-boundary sentence in particular enumerates unrelated action types (reversible save, evidence record, plan refresh) that add little for a pure read tool.

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?

Behaviorally rich for a read tool — covers privacy, auth roles, environment, and idempotency — and does describe the possible return states despite there being no output schema. The gaps are the undocumented parameters and the absence of explicit sibling routing, which leave the definition short of fully self-sufficient.

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 description says nothing about companyId, applicationId, or the nested _corply_context object. The parameter names hint at meaning and the schema encodes UUID formats, but the description contributes no compensating semantics for the three parameters, so it fails the burden it carries at low coverage.

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 ('get_bank_onboarding_status') and describes exactly what it returns: a Mercury prefill handoff, an in-flight/reconciliation state, or the direct Mercury fallback. Its 'First tool for opening a company bank account' framing implicitly positions it ahead of siblings like start_bank_onboarding and reconcile_bank_onboarding, but it never names those alternatives explicitly.

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?

The prerequisite ('authenticated active company access') and the confirmation boundary give some usage context, and 'First tool' implies it precedes the other bank-onboarding siblings. However, it never states when to prefer this over start_bank_onboarding or reconcile_bank_onboarding, so routing guidance is only implied.

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