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

Beyond the annotations (readOnlyHint=false, destructiveHint=false), it discloses that calling starts Stripe KYC (1–5 days), that 'choice_required' started nothing, and that 'guide' created nothing while listing alternatives. This is rich operational context the annotations cannot convey.

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?

Content is front-loaded (mode semantics first, then status handling) and every sentence carries instructions. It is dense and multi-clause, which slightly taxes readability, but there is little waste.

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 explains the meaningful result states (choice_required with options, guide with alternatives), KYC timing, the required user confirmation, and the polling partner tool — everything an agent needs to invoke and follow up correctly.

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 only 60%, but the description compensates well: it explains that 'new' is the fallback for oauth, that reuseAccountId comes from a choice_required result's options, and that forceNew forces a new account. payoutCountry and projectId semantics are largely carried by the schema, so a small residual gap remains.

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 verb+resource ('connect their Stripe account ... or create one') with a clear outcome ('let the user's app take payments'), and distinguishes the two modes by name. It is easily separable from siblings like connect_github, create_checkout, or topup_link.

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?

It explicitly routes the agent: use 'oauth' vs 'new', 'new' is the fallback when oauth fails, confirm with the user first, poll lavela.get_status for the link, and handle 'choice_required' vs 'guide' with concrete next actions. It even names lavela.payments_options as the advanced alternative for narrowing options.

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