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

The description adds valuable behavioral context beyond annotations: the connection happens in the browser, no Refine sign-in is required, and the link is tied to the account owner. It clarifies the tool's role as a link generator rather than a direct connection, which is helpful for the agent. No contradiction with annotations; the description's 'get a link' aligns with readOnlyHint=false (since the user performs the actual connection).

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?

The description is three sentences, each serving a clear purpose: purpose (what it returns and for what), mechanism (how permission is selected), and security warning. It is front-loaded with the primary action and wastes no words. Excellent conciseness and structure.

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 tool with no parameters and a simple action (retrieving a link), the description is complete. It explains the purpose, the flow, and an important security constraint. The presence of an output schema likely covers the return value, so the description doesn't need to. Nothing essential 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?

With zero parameters, the schema already covers everything (100% coverage by definition). The description does not need to explain parameters, and it doesn't. Baseline for no params is 4, and the description appropriately focuses on output and use, so this score is justified.

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 clearly states the tool's function: 'Get a link for the user to connect Gmail to Refine or approve a missing Gmail permission.' It uses a specific verb ('get') and resource ('a link'), and explicitly mentions the two related use cases. This distinguishes it from siblings like integrations.list, which is about listing integrations, not connecting Gmail.

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?

The description provides solid context: it tells the agent it's for connecting Gmail to Refine or approving missing permissions, and that Refine selects the permission. It also includes a critical security caveat: 'Share the link only with the owner of this Refine account.' However, it does not explicitly mention when not to use this tool or name alternative tools, so it falls short of a 5.

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