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

Annotations already flag destructiveHint=true and readOnlyHint=false. The description adds valuable context about approval governance: list/read and content drafts can be approved once per connection, while publish/send and spend actions require per-send human approval. This goes beyond the structured annotations and clarifies the operational behavior without contradicting them.

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 sentences with no fluff: the core action, a discovery prerequisite, and the relevant approval policy. The structure is front-loaded with the main purpose and then adds necessary context. Every sentence earns its place.

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 generic dynamic dispatcher, the description covers the essential workflow: use list_integrations first, then execute. The approval policy adds important operational context. It doesn't document error handling or the shape of arguments, but those are inherently integration-specific and cannot be generalized. Output schema is absent, yet the description doesn't attempt to explain return values, which is acceptable for a pass-through tool.

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?

All four parameters are fully described in the schema (100% coverage), so the baseline is 3. The description adds a small but useful hint that tool_name (and implicitly arguments) should come from list_integrations output, but it doesn't elaborate further. This meets but doesn't exceed the baseline.

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 states a specific verb and resource: 'Execute a tool on a connected MCP integration.' It also distinguishes itself from list_integrations by explicitly directing the agent to use that sibling first to discover available tools. This makes the tool's role unambiguous.

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 gives an explicit prerequisite ('First use list_integrations to discover available tools') and provides policy context on when approvals are required for outbound actions. However, it doesn't mention when to prefer dedicated sibling tools like send_email or publish_shopify_product over this generic invoker, which is a minor gap.

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