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

The annotations already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true, so the agent knows this is a safe read. The description adds behavioral value by disclosing what 'toolkit state' means: installed MCPs, connection status, accounts, and catalog tool counts. This is a good example of the description supplementing the annotations, not contradicting them. It doesn't disclose potential latency or whether connection status is live, but for a recursive info tool, this is appropriately transparent.

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 a single, information-dense sentence that covers what the tool returns without wasted words. Every clause earns its place: 'installed MCPs,' 'connection status,' 'accounts connected to each one,' and 'catalog tools each exposes.' No fluff, perfectly scoped.

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 zero-parameter, read-only info tool with no output schema, the description completely captures the return payload. It doesn't need to enumerate return formats since there's no output schema, and for an agent needing toolkit state, the description is unambiguous. The tool is a trivial introspection command, and the description is perfectly calibrated to that complexity.

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 0 parameters and baseline score 4 for parameter semantics, the description is not required to add parameter info. The description focuses on return-value semantics instead, which is appropriate since there are no parameters. No deduction needed since there are no parameters left undocumented.

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 clear specific verb 'Returns' with a specific resource 'current toolkit state' and details what it contains (installed MCPs, connection status, accounts, catalog tools). It distinguishes from siblings like 'show_version' and 'marketplace' by focusing on MCP/account/catalog tooling rather than version or marketplace information.

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 implies when to use this tool: when an agent needs information about installed MCPs, their connection status, connected accounts, or catalog tool counts. It doesn't explicitly name alternatives or when-not-to-use, but the sibling-context and 'current toolkit state' framing provides clear context for when this is the right tool versus others like 'marketplace' or 'show_version'. A point is deducted for not explicitly calling out alternatives.

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