Create a revenue integration (201); all secrets are write-only

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

Annotations already declare readOnlyHint=false and openWorldHint=true, and the description adds meaningful context on top: the two-step confirm gate, the absence of a server-side dry run, the 201 response, and the fact that secrets are write-only after creation. It stops short of stating required auth scopes, what happens to an existing integration with the same label, or how the returned preview is shaped.

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: the operation and endpoint first, then the write-gate constraint. No filler, no restatement of the schema, and the most safety-critical information (confirm gate) is front-loaded after the core purpose.

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 mutating creation tool with no output schema and a nested body, the description covers the critical gaps: it is a write, it needs explicit confirmation, there is no dry run, and secrets are never returned. What is missing is field-conditional guidance across the three integration kinds and any indication of error or conflict behavior.

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 67%, and confirm and idempotencyKey already carry their own schema descriptions, so the schema does most of the work. The one real addition is "all secrets are write-only," which tells the agent that webhookSecret, apiKey, accessToken, and similar body fields cannot be read back. The nested body properties (shopDomain, clientId, consumerKey, baseUrl) remain undocumented in both places, and which fields are required per kind is never explained.

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 gives a specific verb and resource ("Create a revenue integration"), plus the HTTP method and path (POST /v1/revenue/integrations) and the expected 201 outcome. It does not, however, distinguish this tool from nearby siblings such as revenue_listIntegrations, connections_create, or conversions_setIntegration, so an agent must infer where this belongs from the name alone.

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 clearly states the execution precondition ("not executed unless confirm: true") and warns there is no server-side dry run, which is genuinely actionable. It gives no guidance on when to pick this over the connections_* or conversions_setIntegration tools, and no prerequisites or field-per-kind requirements are mentioned, so usage is only partially framed.

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