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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds real behavior on top: it returns a secure Stripe authorization link when needed and explicitly reassures the agent not to recreate or rotate anything on re-call. This is useful context beyond the safety hints, though return shape and any auth requirements are not detailed.

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?

Three tight sentences, front-loaded with what is checked, followed by the Stripe special case and the re-call instruction. No filler; each sentence carries 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 properly enumerates the return contents and the conditional Stripe auth link, which is the key thing an agent needs. For a single-param read tool this is nearly complete; only sourceId semantics remain thin.

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?

One parameter (sourceId) at 0% schema coverage means the schema provides no documentation, so the description must compensate. 'Check a source's ...' implies that sourceId identifies the source, adding marginal meaning, but it gives no format, ID type, or lookup guidance.

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 (Check) and enumerates exactly what the response aggregates: provider connection, enabled destinations, signature-verified events, and delivery attempts. It is clearly a status/diagnostic read distinct from the mutating siblings. It stops short of naming the nearest sibling (ensure_webhook_setup), so it is differentiated more by detail than by explicit contrast.

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?

Gives concrete usage context: call it to check, then 'call again after the user connects'. That polling instruction is a genuine when-to-use signal. It does not, however, state when to prefer it over ensure_webhook_setup or other setup tools, so no explicit alternatives or exclusions.

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