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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the agent knows it's a safe, non-mutating call. The description adds context about the content (connection statuses, accounts, catalog tool counts) beyond what annotations provide. It doesn't describe any edge cases (e.g., what happens if no MCPs are installed) or error conditions, but given the rich annotations, this is acceptable. No contradiction with annotations.

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?

Single sentence, front-loaded with the primary action ('Returns the current toolkit state'), then a concise enumeration of included details. No wasted words, no repetition of schema or annotations. Ideal length for a zero-parameter tool.

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 tool's simplicity (0 parameters, no output schema, annotations covering safety), the description is complete enough. It tells the agent exactly what to expect in the response and implicitly confirms this is a read-only snapshot. It doesn't mention any potential latency or need for prior authentication, but that's a minor gap for a status tool. Sibling tools like 'connect' and 'authenticate' suggest this might be called before/after those, but the description doesn't address ordering prerequisites, though that might be over-engineering for this tool.

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 0 parameters, and the schema is empty. With no parameters, the baseline is 4 per the rubric. The description's job here is to clarify the returned content, which it does ('installed MCPs, connection status, accounts, how many catalog tools'). Since there are no parameters to explain, this high score is appropriate.

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 purpose with specific context: 'Returns the current toolkit state' and enumerates the exact contents (installed MCPs, connection status, accounts, catalog tools). The verb 'Returns' plus resource 'toolkit state' is clear. However, the sibling tools (authenticate, connect, marketplace) suggest this is a diagnostics/status tool but the description doesn't explicitly contrast it with 'show_version' style info tools, so it lacks a direct sibling differentiation statement.

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 usage as an inspection/diagnostic tool: you'd call it to see the current state of MCPs and accounts. But it doesn't explicitly state when to use it versus alternatives like 'show_version' or 'report_bug'. There's no guidance on when NOT to use it or when another tool would be preferred. For a read-only diagnostic tool, this is adequate but lacks explicit decision criteria.

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