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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the description's job to disclose side effects is light. However, it adds value by detailing what state is returned (MCPs, statuses, accounts, catalog counts), which is not in the annotations. It does not explicitly state 'no changes are made,' but the combination of annotations and 'Returns the current state' covers it. The description gives expected details without needing a warning.

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, well-structured sentence that lists all key elements without redundancy. It is front-loaded with the verb 'Returns' and immediately specifies the domain ('toolkit state'), then enumerates the specific components. Every word adds value, and the colon-separated list is readable. No fluff or unnecessary detail.

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 has no parameters and no output schema, the description is complete in covering the tool's purpose and the content of what it returns. It addresses all aspects a user would need to know to decide to call it: what is returned, and implicitly, when to use it (e.g., to check connection status). The description is fully sufficient for a stateless read-only info 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?

There are zero parameters and schema coverage is 100% (empty schema), so the description needs no parameter clarification. The description remains useful by explaining what the returned information covers, adding context beyond the empty input schema. This is a case where the schema is trivial, so the description adds clarity about the tool's behavior. A score of 4 is warranted because it goes beyond the schema's silence by setting expectations about output content.

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 ('Returns') and identifies the resource ('current toolkit state') with concrete details: 'installed MCPs, their connection status, the accounts connected to each one, and how many catalog tools each exposes.' It clearly distinguishes itself from siblings like `authenticate` and `marketplace` by focusing on state inspection. The purpose is immediate and unambiguous.

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?

Though there is no explicit 'when to use' or 'when not to use' statement, the description clearly implies a read-only diagnostic use case, contrasting with sibling tools like `connect` or `authenticate` that likely perform actions. The lack of parameters and readOnlyHint annotation further signal it should be used first to understand the environment. It lacks explicit exclusions or alternatives, but the context is strong.

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