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

Annotations already declare readOnly=false, idempotent=false, openWorld=true, destructive=false. The description goes beyond them usefully: it describes the return payload (connection status plus a single-use onboarding URL), states the URL is single-use and owner-completable, and defines the 'ready' terminal state. That is meaningful workflow context the annotations do not carry.

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?

Two tight sentences, front-loaded with the purpose before the return-value and permission details. No filler.

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 correctly explains what comes back and the ready-state semantics, and flags the owner-only restriction. Minor gap: it doesn't say what a repeated call yields given idempotent=false, though the single-use URL wording hints at it.

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?

Only one parameter (siteId) and schema description coverage is 100%, with the schema itself instructing 'Pass it on every call.' Baseline 3 applies; the description adds nothing further about the parameter.

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 ('Connect Stripe') plus the outcome ('so the site can take payments'), which separates it cleanly from the stripe_get_product / stripe_search_products siblings that deal with catalog data. An agent can tell this is the payment-connection setup tool without opening the schema.

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 description implies the usage context (initial Stripe setup) and names a hard constraint ('Owner-only'), but it never states when to call this versus other integration tools (set_integrations, set_checkout) or what to do on subsequent calls. Usage is inferable rather than explicit.

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