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

Annotations only supply readOnlyHint=false/destructiveHint=false; the description adds the real behavioral payload: this kicks off Stripe KYC (1-5 days), requires user confirmation, and that the onboarding link must be retrieved by polling lavela.get_status. It also clarifies that a 'choice_required' result is a no-op that started nothing, which prevents an agent from treating it as progress.

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-loads purpose, then behavior, then the edge case, and the doc link trails at the end where it belongs. It is dense and slightly compressed (parentheticals, em-dashes) but nearly every clause carries decision-relevant information.

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?

With no output schema, the description still covers the state machine an agent must handle (oauth failure fallback, choice_required semantics, KYC wait + status polling), which is the hard part. It omits what the call itself returns and any error surface, leaning on the docs link for that residue, so it is complete but not exhaustive.

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 50% (mode and projectId undocumented). The description compensates by defining the meaning and triggering condition of mode 'oauth'/'new', the role of reuseAccountId ('an accountId from a choice_required result's options', mode 'new' only), and forceNew:true as the always-create overwrite. Only projectId is left unexplained, hence not a 5.

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 the specific verb and resource ('connect their Stripe account') and immediately splits the two modes of operation ('oauth' vs 'new'), which is what an agent needs to tell this apart from connect_github and the other connect_* siblings.

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?

Explicit when-to-use for every branch: mode 'oauth' to connect an existing account, mode 'new' as the documented fallback when oauth fails, and for a 'choice_required' status it names the two alternatives (reuseAccountId from options vs forceNew:true) selected by user preference. It also names the prerequisite action ('confirm with the user first').

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