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

Goes well beyond the annotations (which only state it is a non-read-only, non-destructive write). It discloses webhook registration, that money never passes through Conecto, that the key is encrypted and never shown again, that the link costs nothing, and the exact cost ($0.001 per call, free on failure). Rich operational context an agent cannot get from structured fields.

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-loaded with the core purpose and enabling condition, and nearly every clause earns its place (key creation steps, webhook, money flow, encryption, cost). It is dense and runs long with nested parentheticals, so structure could be cleaner, but there is little pure 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?

For a mutation/connect tool with no output schema, the description supplies what the agent needs: what happens on success (account.credential_added), the credential-security model, cost, and the no-key fallback path. Nothing essential is missing.

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 100% and the parameter is already documented, so baseline is 3. The description adds meaningful semantics: what kind of key it is (restricted, rk_live, write access to Checkout Sessions/Webhook Endpoints), where the owner creates it, and the omit-to-get-a-link behavior, which explains the parameter's optionality beyond the schema.

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 the business's Stripe account) and names exactly what it enables (a Pay button via invoices_set_profile pay_online). An agent can distinguish it from sibling invoice tools 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?

Explicitly describes the two invocation modes: pass stripe_key to connect directly, or omit it to receive a link for the owner. It also names the terminal alternative (from_a_terminal) and the downstream signal (account.credential_added). It stops short of saying when-not to use or prerequisites for other invoice flows, so not a full 5.

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