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

readOnlyHint and openWorldHint already cover the safety profile, so the description's additional value is the disclosure that switched-off connections are still returned and that each entry carries the tool-name prefix — non-obvious output behavior that shapes downstream calls. It stops short of describing ordering, error behavior, or whether authorization is needed.

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?

One sentence, front-loaded with the core action and resource, then the two scoping facts that matter. Zero waste.

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?

With no params, no output schema, and annotations covering read-only semantics, the definition supplies just enough: what is listed, that inactive ones appear, and what identifying field comes back. Minor gaps remain around result shape/ordering and whether a connection identifier is included alongside the prefix.

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?

Zero parameters with an empty object schema, so baseline 4 applies; there is nothing for the description to compensate for. It correctly adds no parameter chatter.

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?

Specific verb+resource ('List the MCP servers connected through this OnlyMCP account') with useful scope qualifiers: disabled connections included and each entry's tool-name prefix. It doesn't explicitly name how it differs from neighbors like connection_tools or connection_call, so an agent must infer that this is the account-level inventory rather than a per-connection tool dump.

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?

Usage is only implied: an agent can reason that this is the discovery step before connection_call/connection_tools, but the description never states when to choose it or when a sibling is more appropriate. No prerequisites or exclusions are given.

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