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

With readOnlyHint, idempotentHint, and destructiveHint already declared, the description adds genuine value by specifying exact response shapes for different system states (empty pending[], connect_url, per-install URLs). It reinforces the read-only contract without contradicting any annotation.

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?

Exactly three sentences, each carrying distinct weight: core function, success condition, and failure/fallback condition. There is zero redundancy. The structure mirrors the tool's internal logic, making it highly scannable and easy to reason about.

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 parameterless, side-effect-free tool with a rich set of annotations and a detailed prose description, this is very complete. The only gap is a potential 'partial connection' edge case that the binary framing ('all connected' vs 'missing credentials') might not fully cover.

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 baseline is 4. The description wisely communicates that the tool requires no arguments — it derives state itself. The behavioral description of what varies (connection state, URLs) is all the semantic context an agent needs for a 0-arg tool.

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 uses a specific verb+resource ('Returns connection status and URLs') and enriches it with state-dependent behavior ('When all providers are connected... When credentials are missing...'). The conditional return values clearly distinguish this status-check tool from siblings like 'authenticate' without any ambiguity.

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?

While the description never explicitly names alternatives (e.g., 'use authenticate to initiate'), the clear state-outcome mapping ('returns authenticated:true', 'returns connect_url') implicitly teaches the agent that this is the go-to gor status polling. It provides clear context for when to call this (to check connection state), even if it never explicitly says when *not* to call it.

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