Create a CRM connection

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

Annotations already declare readOnlyHint=false, destructiveHint=true, idempotentHint=false, openWorldHint=false, so the safety profile is covered. The description adds real value beyond them: required scopes (integrations:write, luca:full), data sensitivity level, the Idempotency-Key requirement, and that the server will generate a key if omitted. This last point usefully clarifies how safe retries work despite idempotentHint=false.

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 action, followed by structured metadata lines (operation, scopes, idempotency, workspace override). No filler sentences. The metadata lines are somewhat boilerplate but each carries operationally relevant 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?

An output schema exists, so return values need not be explained. Auth, idempotency, and workspace targeting are covered for a mutation tool with a nested body. The remaining gap is the ambiguity of the create-vs-update path and what 'redacted' sensitivity implies, but nothing critical for a correct call 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 description coverage is 75%, so the schema already documents workspaceId, workspaceSlug, and idempotencyKey. The description adds meaning to the idempotency behavior ('or the server will generate one') and the workspace override. It does not explain the nested body structure (provider enum, credentialsRef pattern, settings), which is the most error-prone part of the call.

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 opens with a specific verb+resource: 'Create or update a workspace-scoped CRM connection,' and the operation line (POST /api/integrations/crm/connections) confirms the endpoint. It distinguishes itself from siblings like connections_list, connections_schema, and connections_health by scope and action. The 'create or update' upsert framing is honest but slightly muddies what the tool actually does versus its 'create' name.

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 explains the workspaceId/workspaceSlug override behavior and idempotency handling, which is useful context. However, it never routes the agent among alternatives (e.g., when to use this versus connections_list or crm_oauth_url), nor does it explain when an update path is taken over a create. Usage is implied by the endpoint semantics rather than stated.

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