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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds useful detail: it specifies the exact return contents (installed MCPs, connection status, accounts, catalog tool counts). It does not contradict annotations. It provides a clear, non-destructive read-only behavior, enhancing what the annotations communicate. It doesn't mention potential latency or rate limits, but for a status query that's acceptable.

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 sentence that lists all relevant information categories compactly without redundancy. It is front-loaded with the main action ('Returns the current toolkit state') and then enumerates the specifics. No wasted words.

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?

Given the output schema is absent (only a generic object), the description does a good job of explaining what the return will include. For a zero-parameter tool, this is sufficient. It covers the key aspects: what the state includes and what it doesn't (actions). It could optionally mention that it reflects current connections, but the phrase 'current toolkit state' already implies that. It's complete enough for an agent to invoke without confusion.

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?

The tool has zero parameters, so there is nothing to explain. The description accurately describes the state snapshot returned, which is the only 'input' context. Since no parameters exist, the description effectively covers all input semantics. Baseline for 0 params is 4, and no further info is needed.

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 starts with 'Returns the current toolkit state' – a specific verb and resource ('toolkit state'). It enumerates the exact contents: installed MCPs, connection status, connected accounts, and catalog tool counts. This clearly distinguishes it from sibling tools like 'authenticate' or 'connect', which handle specific actions rather than state reporting.

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 makes the tool's purpose evident: querying the current state of the toolkit. Given the sibling names (authenticate, connect, marketplace, etc.), this tool is clearly for orientation/inspection. However, it does not explicitly state when to use it versus alternatives, but the clear purpose implicitly signals it is for state inspection, not for actions. Missing explicit exclusions (e.g., 'if you need to modify, use ...') but the context makes it obvious.

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