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

With no annotations, the description carries the full burden and does so thoroughly. It discloses side effects (creates a one-click approval card), conditional behavior (allowlist vs. vet request), non-effects (never spends money, does not connect anything), and process context (sensitive-tier, multi-step, still needs OAuth/connect card).

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?

Every sentence earns its place. The core purpose and required inputs are front-loaded, followed by behavioral caveats and role-specific context. The bracketed sensitive-tier note adds useful process context without bloating the primary instruction.

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 sensitive, multi-step request tool with no annotations and no output schema, the description is unusually complete. It covers what the tool does, how to invoke it, role differences, allowlist behavior, and downstream connection requirements. An agent has enough context to call it correctly and understand the follow-up flow.

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 each parameter already has a clear description. The tool description adds modest reinforcement ('from search_connector_registry', 'short reason') but does not meaningfully extend the schema's parameter documentation. Baseline 3 is appropriate because the schema does the heavy lifting.

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 action ('request that the operator connect an external integration'), names the resource ('MCP connector'), and clarifies what it is not ('does not connect anything by itself'). It is clearly distinguishable from siblings like invoke_integration and confirm_mcp_approval without needing to inspect their schemas.

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 clear context on when to call this tool: when an external connector capability is needed, with the name sourced from search_connector_registry. It also explains role-based behavior (managers run without a card; other members ask once). It does not explicitly name alternative tools for when a connector is already granted, but the request≠grant note and 'does not connect anything by itself' convey the boundary.

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