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

Goes well beyond the annotations (readOnlyHint=false, openWorldHint=true, destructiveHint=false): discloses the provider-side read-only nature, that no sensitive data is exposed, that no money moves, that the run is hash-bound and recorded, and the subtle first-run anchoring rule with fail-closed variance behavior. The recording side effect is consistent with readOnlyHint=false; no contradiction with 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?

The core purpose is well front-loaded in the first sentence, but roughly half the description is generic boilerplate (Canonicality, Idempotency, Confirmation boundary) that appears to be appended across many tools, including the self-referential 'plus every prerequisite stated above' and the enumerated confirmation-boundary categories. It is informative but padded.

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?

Covers side effects, safety constraints, the anchoring rule, prerequisites, and retry guidance well. However, with no output schema, it never describes the shape of the returned reconciliation result, and it omits how to source the routeId (e.g., from route-draft or onboarding tools). Gaps remain for a tool that records state and can fail readiness.

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 only 33% (only _corply_context is described in-schema), so the description must compensate. It partially helps for routeId via 'route-scoped platform-cash postings', but companyId receives no explanation anywhere, and the description never addresses _corply_context or how to obtain a valid routeId. Compensation is incomplete.

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?

The description states a specific multi-step operation: read the active Moov sandbox wallet balance, compare against Corply route-scoped postings, and record a hash-bound reconciliation run. It clearly distinguishes this from sibling tools like run_sandbox_payment_probe and reconcile_bank_onboarding by explicitly noting it makes provider reads only, moves no money, and exposes no account/credential data.

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 clear tool-specific context: the first run may only anchor a pre-existing balance before any payment/journal activity, later variance fails readiness closed, and authenticated active organization access is a prerequisite. The canonicality note adds an explicit exclusion ('trust the returned output... instead of adding a state-recovery call'), though it never names alternative sibling tools directly.

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